CN105679318A - Display method and device based on voice recognition, display system and air conditioner - Google Patents
Display method and device based on voice recognition, display system and air conditioner Download PDFInfo
- Publication number
- CN105679318A CN105679318A CN201510993344.1A CN201510993344A CN105679318A CN 105679318 A CN105679318 A CN 105679318A CN 201510993344 A CN201510993344 A CN 201510993344A CN 105679318 A CN105679318 A CN 105679318A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- speech
- current
- prestored
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 125
- 230000006870 function Effects 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000003213 activating effect Effects 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 89
- 238000004458 analytical method Methods 0.000 claims description 54
- 230000004913 activation Effects 0.000 claims description 21
- 230000007613 environmental effect Effects 0.000 claims description 20
- 238000004378 air conditioning Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000012856 packing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 230000007480 spreading Effects 0.000 claims description 6
- 230000007547 defect Effects 0.000 abstract description 3
- 230000003993 interaction Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000004899 motility Effects 0.000 description 10
- 230000002452 interceptive effect Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000001737 promoting effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000001143 conditioned effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a display method, a display device, a display system and an air conditioner based on voice recognition, wherein the display method comprises the following steps: performing voice recognition processing on voice information input within a preset environment range, and activating a voice command input mode when the current voice information is determined to be voice information; extracting a voice input command carried by current voice information, and issuing the extracted voice input command according to a preset command type to obtain a completion result of the voice input command; and exiting the voice command input mode based on the completion result obtained by the issuing processing. The scheme of the invention can overcome the defects of few functions, poor interaction flexibility, poor user experience and the like in the prior art, and has the beneficial effects of more functions, good interaction flexibility and good user experience.
Description
Technical field
The present invention relates to electronic display technology field, in particular it relates to a kind of based on the display packing of speech recognition, device, display system and air-conditioning.
Background technology
Display panel, it is possible to be the LED display board being series at one piece of pcb board by the LED of a lot of, it is also possible to be the circuit board with real function with liquid crystal display screen and charactron. Display panel is energized, under the control of control circuit, it is possible to the required content of display.
At present, the information between user and display panel is mutual, is required for relying on display panel. And for the operation of display panel, it is typically all the button or touch screen that directly operate display panel, seldom there is other mode of operation. This information interaction approach, being not easy between user, information is mutual more, affects Consumer's Experience; It addition, when user's inconvenient directly operation display panel, cannot use corresponding function, the use scope of corresponding function or frequency reduce, and the convenience that user uses also reduces.
In prior art, there is the defects such as function very flexible few, mutual and poor user experience.
Summary of the invention
It is an object of the invention to, for drawbacks described above, propose a kind of based on the display packing of speech recognition, device, display system and air-conditioning, process is issued with what solve to be detected in real time the control carrying out voice command input pattern and respective voice by acoustic information, process voice command more accurately, promote mutual motility, reduce the problem of mutual difficulty, thus reaching that function motility many, mutual is good and the effect such as Consumer's Experience is good.
One aspect of the present invention provides a kind of display packing based on speech recognition, including: the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, activates voice command input pattern; Extract the phonetic entry order carried of current speech information, and issue process by default command type to extracting the described phonetic entry order obtained, complete result with what obtain described phonetic entry order; Based on described issue process obtain described in complete result, exit institute's speech commands input pattern.
Wherein, the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, activate voice command input pattern, including: the acoustic information of input in environmental field is preset in detection in real time, and when there being acoustic information to input, according to the voice packet prestored, described acoustic information is carried out examination process, to determine that whether current sound information is for voice messaging; When described acoustic information is voice messaging, described voice messaging is sequentially carried out filtration and processes with similar fractional analysis, to obtain described similar fractional analysis result; When described similar fractional analysis result meets default voice command activation condition, activate voice command input pattern.
Wherein, extract the phonetic entry order that current speech information is carried, and issue process by default command type to extracting the described phonetic entry order obtained, including: the key word of current speech information is captured by predeterminated frequency, the voice command bag prestored based on this keyword search is to extract the phonetic entry order corresponding with current speech information, and based on default command type and the command type extracting the described phonetic entry order that the described phonetic entry order obtained carries out contrasting determining that extraction obtains; Based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information.
Preferably, based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information, including: when determining that described phonetic entry order is querying command, after carrying out inquiry automatically in preset duration, directly play the information inquired about needed for current speech information with linguistic form, complete current queries order. Wherein, the information of the required inquiry of described current speech information, including: the prestored information corresponding with described querying command and/or more fresh information; And/or, automatically inquire about in preset duration, including: multiple queries condition current speech information comprised is by the sequencing of input, after postponing the mode of preset duration successively and being sequentially completed corresponding query processing, by the querying command end rules preset, terminate current queries order.
Based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information, also include: when determining that described phonetic entry order is setting command, directly point out the currency of configuration information needed for current speech information with speech form and ask whether, with linguistic form, the expected value that needs to reset this configuration information for current speech information; Afterwards, according to user's voice feedback information in preset duration, automatically arrange in preset duration, complete current setting order; If the user while be not based on the voice feedback information of described inquiry in preset duration, then the currency giving tacit consent to described prompting is expected value, completes current setting order. Wherein, automatically arrange in preset duration, including: what current speech information comprised multiple arranges the conditions sequencing by input, after postponing the mode of preset duration successively and being sequentially completed and arrange process accordingly, by the setting command end rules preset, terminate current setting order.
Wherein, based on described issue process obtain described in complete result, exit institute's speech commands input pattern of current speech information, including: after completing current described phonetic entry order, ask the user whether to need to perform other orders with speech form, and based on user's feedback of speech form in preset duration, carry out respective handling by the command type of this feedback voice; And, when not receiving user in preset duration based on the feedback of the speech form of described inquiry, automatically exit from current voice command input pattern.
Further, learnt by this locality and/or cloud computing and/or program upgrading mode, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice are carried out online upgrading and/or renewal processes, to obtain described voice packet and/or the spreading result of voice command bag and/or prestored information.
Further, learnt by this locality and/or cloud computing and/or program upgrading mode, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice carry out online upgrading and/or renewal processes, including: collect including at least local language, conventional term and use habit be collected locally information, it is collected locally after information is analyzed to described, based on analyzing result Auto-matching user, and/or delete in the institute's speech commands bag prestored untapped data in preset duration, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed, and/or, by cloud computing, the described information that is collected locally is sent to server, carry out secondary analysis by server, after secondary analysis results verification, automatically download the user based on secondary analysis result and use data, and/or, increasing up-to-date user data by cloud computing, this user data comes from network collection information and the analysis result to network collection information, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed, and/or, the upgrading of the program being upgraded by difference and/or normally upgrade, the described voice packet prestored and/or the institute's speech commands bag and/or the prestored information corresponding with respective voice that prestore are carried out online upgrading.
Further, the method also includes: under institute's speech commands input pattern of described activation, and/or, based on described issue process obtain described in complete result, automatically display and/or point out the current spendable phonetic function of user with speech form.
Match with said method, another aspect of the present invention provides a kind of display system based on speech recognition, including: voice recognition unit, for the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, activate voice command input pattern; Order issues unit, for extracting the phonetic entry order that current speech information is carried, and issues process by default command type to extracting the described phonetic entry order obtained, and completes result with what obtain described phonetic entry order; Pattern exits unit, for based on described issue process obtain described in complete result, exit institute's speech commands input pattern.
Wherein, voice recognition unit, including: sound screens module, for detecting the acoustic information of input in default environmental field in real time, and when there being acoustic information to input, according to the voice packet prestored, described acoustic information is carried out examination process, to determine that whether current sound information is for voice messaging; Voice pretreatment module, for when described acoustic information is voice messaging, being sequentially carried out filtration and process with similar fractional analysis, to obtain described similar fractional analysis result to described voice messaging; Mode activation module, for when described similar fractional analysis result meets default voice command activation condition, activating voice command input pattern.
Wherein, order issues unit, including: determination type module, for capturing the key word of current speech information by predeterminated frequency, the voice command bag prestored based on this keyword search is to extract the phonetic entry order corresponding with current speech information, and based on default command type and the command type extracting the described phonetic entry order that the described phonetic entry order obtained carries out contrasting determining that extraction obtains; Ordered module, for based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information.
Preferably, order module, including: querying command completes submodule, for when determining that described phonetic entry order is querying command, after carrying out inquiry automatically in preset duration, directly play the information inquired about needed for current speech information with linguistic form, complete current queries order. Wherein, the information of the required inquiry of described current speech information, including: the prestored information corresponding with described querying command and/or more fresh information; And/or, querying command completes submodule, including: automatically inquire about submodule, for sequencing by input of multiple queries condition that current speech information is comprised, after postponing the mode of preset duration successively and being sequentially completed corresponding query processing, by the querying command end rules preset, terminate current queries order.
Order module, also include: setting command completes submodule, for when determining that described phonetic entry order is setting command, the currency of configuration information ask whether the expected value that needs to reset this configuration information for current speech information with linguistic form needed for directly pointing out current speech information with speech form; Afterwards, according to user's voice feedback information in preset duration, automatically arrange in preset duration, complete current setting order; If the user while be not based on the voice feedback information of described inquiry in preset duration, then the currency giving tacit consent to described prompting is expected value, completes current setting order. Wherein, setting command completes submodule, including: submodule is set automatically, for current speech information is comprised multiple arrange conditions by input sequencing, after postponing the mode of preset duration successively and being sequentially completed process is set accordingly, by the setting command end rules preset, terminate current setting order.
Wherein, pattern exits unit, including: continue with module, after completing current described phonetic entry order, ask the user whether to need to perform other orders with speech form, and based on user's feedback of speech form in preset duration, carry out respective handling by the command type of this feedback voice; And, module is exited in time delay, for when not receiving user in preset duration based on the feedback of the speech form of described inquiry, automatically exiting from current voice command input pattern.
Further, this system also includes: functional expansion unit, for passing through this locality study and/or cloud computing and/or the mode of program upgrading, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice are carried out online upgrading and/or renewal processes, to obtain described voice packet and/or the spreading result of voice command bag and/or prestored information.
Wherein, functional expansion unit, including: local study module, it is collected locally information including at least local language, conventional term and use habit for collecting, it is collected locally after information is analyzed to described, based on analyzing result Auto-matching user and/or deleting in the institute's speech commands bag prestored untapped data in preset duration, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or, cloud computing module, for being sent the described information that is collected locally to server by cloud computing, carry out secondary analysis by server, after secondary analysis results verification, automatically download the user based on secondary analysis result and use data; And/or, increasing up-to-date user data by cloud computing, this user data comes from network collection information and the analysis result to network collection information; To realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or, program upgraded module, for the program upgrading upgraded by difference and/or normally upgrade, the described voice packet prestored and/or the institute's speech commands bag and/or the prestored information corresponding with respective voice that prestore are carried out online upgrading.
Further, this system also includes: function display unit, is used under institute's speech commands input pattern of described activation, and/or, based on described issue process obtain described in complete result, automatically display and/or point out the current spendable phonetic function of user with speech form.
Matching with said method and/or device, further aspect of the present invention provides a kind of display system, including: devices discussed above.
Matching with said method and/or device and/or display system, another aspect of the invention provides a kind of air-conditioning, including: above-described display system.
The solution of the present invention, that is detected the control carrying out voice command input pattern and respective voice in real time by acoustic information issues process, using phonetic entry as display interactive mode, user's dependence to traditional display modes (such as: the mode that display panel is directly operated) can be reduced, by the mode such as speech exchange, order, it is possible to achieve show function (such as: what display panel carried out directly operation shows function accordingly) accordingly or read the data of unit (such as: air conditioning unit).
Further, the solution of the present invention, by the function of phonetic entry being extended and/or updating, (such as: by display panel auxiliary display) the relevant parameter information of the auxiliary display when voice operating or information, phonetic entry can be improved as the motility of interactive mode of display and versatility, promote Consumer's Experience further.
Thus, the solution of the present invention solves to utilize what acoustic information detected the control carrying out voice command input pattern and respective voice in real time to issue process, process voice command more accurately, the problem promoting mutual motility, reducing mutual difficulty, thus, overcome the defect of the very flexible few, mutual of function in prior art and poor user experience, it is achieved the function beneficial effect that motility is good and Consumer's Experience is good many, mutual.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from description, or understand by implementing the present invention.
Below by drawings and Examples, technical scheme is described in further detail.
Accompanying drawing explanation
Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, is used for together with embodiments of the present invention explaining the present invention, is not intended that limitation of the present invention. In the accompanying drawings:
Fig. 1 is the present invention flow chart based on an embodiment of the display packing of speech recognition;
Fig. 2 be the present invention method in the flow chart of an embodiment of voice recognition processing;
Fig. 3 be the present invention method in order issue the flow chart of an embodiment of process;
Fig. 4 is the present invention structural representation based on an embodiment of the display device of speech recognition;
Fig. 5 be the present invention system in ordered the structural representation of an embodiment of module;
Fig. 6 is the structural representation of an embodiment of the display system of the present invention.
In conjunction with accompanying drawing, in the embodiment of the present invention, accompanying drawing labelling is as follows:
102-voice recognition unit; 1022-sound screens module; 1024-voice pretreatment module; 1026-mode activation module; 104-order issues unit; 1042-determination type module; 1044-order completes module; 10442-querying command completes submodule; 104422-inquires about submodule automatically; 10444-setting command completes submodule; 104442-arranges submodule 104442 automatically; 106-pattern exits unit; 1062-continues with module; Module is exited in 1064-time delay; 108-function display unit; 110-functional expansion unit; 1102-this locality study module; 1104-cloud computing module; 1106-program upgraded module; 202-display panel; 204-controls pen.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with the specific embodiment of the invention and corresponding accompanying drawing, technical solution of the present invention is clearly and completely described. Obviously, described embodiment is only a part of embodiment of the present invention, rather than whole embodiments. Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
According to embodiments of the invention, it is provided that a kind of display packing based on speech recognition, as shown in Figure 1 shown in the flow chart of an embodiment of the method for the present invention. The method at least includes:
In step S110 place, the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, to activate voice command input pattern (such as: the voice command input pattern of current speech information). By acoustic information (such as: display panel place environment space) in default environmental field is sampled and is identified, it is possible to promote reliability and the accuracy of the voice command of input; When the voice command of input meets pre-conditioned, activate corresponding voice command input pattern to realize the reliable input of voice command, good energy saving property, functional reliability is high, is conducive to promoting use quality that voice shows and extends the service life that voice shows.
Below in conjunction with the flow chart of an embodiment of voice recognition processing in the method for the present invention shown in Fig. 2, further illustrate the concrete processing procedure of the speech recognition of step S110.
Step S210, the acoustic information of input in environmental field is preset in detection in real time, and when there being acoustic information to input, according to the voice packet prestored, described acoustic information is carried out examination process, to determine that whether current sound information is for voice messaging. By detecting in default environmental field acoustic information (such as: display panel place environment space) in real time, processed by examination and current sound information is carried out preliminary identifying processing, mode of operation is simple, reliable, is conducive to reliability and safety that voice shows.
Wherein, according to the voice packet prestored, described acoustic information is carried out examination process, it is possible to including:
When sound reaches certain frequency (such as: acquiescence 50Hz), acquiescence has sound to input. If sound input time short (such as: estimate in 0.3s), it is believed that current sound is illegal, is not linguistic information; Otherwise, then it is assumed that current sound is voice messaging.
Step S220, when described acoustic information is voice messaging, is sequentially carried out filtration and processes with similar fractional analysis, to obtain described similar fractional analysis result described voice messaging. By the voice messaging determined is carried out pretreatment, to filter out the burr information in voice messaging, it is possible to promote accuracy and the reliability of the voice command of input, also help lifting user's experience.
Wherein, when described acoustic information is voice messaging, described voice messaging is sequentially carried out filtration and processes with similar fractional analysis, it is possible to including:
First, aforementioned examination is processed the sound screened, identifies that it wakes up or command statement. When the voice data translation gathered is that the treatable data of computer (such as: speech recognizer processes output data) reach more than 60% (can set) with the Data Matching degree recorded in advance, then it is assumed that current language information is effective.
Secondly, for long-time phonetic entry, inside not interrupted voice, as inputted at certain time length (such as: in 15s) invalid command, no longer receive discontinuously voice (such as: constantly continued shows that voice stopped to the speech interval time next time less than 2 seconds). Invalid voice input stopping more than 2 seconds after when re-entering voice, again identify voice.
Then, to efficient voice order, in 20 seconds after terminating such as command statement, without subsequent commands, current speech input stops.
Step S230, when described similar fractional analysis result meets default voice command activation condition, activates voice command input pattern (such as: the voice command input pattern of current speech information). Activating corresponding voice command input pattern by aforementioned processing result, safety is good, and reliability is high.
In step S120 place, the phonetic entry order that (such as: can extract under institute's speech commands input pattern of described activation) the current speech information of extraction is carried, and issue process by default command type to extracting the described phonetic entry order that obtains, complete result with what obtain described phonetic entry order. By, under the voice command input pattern activated, extracting voice command in the current speech information of input and perform this voice command, complete the voice display requirement of user so that reliability and motility that voice shows all are improved.
Issue the flow chart of an embodiment of process below in conjunction with order in the method for the present invention shown in Fig. 3, further illustrate the concrete processing procedure that the order of step S120 issues.
Step S310, the key word of current speech information is captured by predeterminated frequency, the voice command bag prestored based on this keyword search is to extract the phonetic entry order corresponding with current speech information, and based on default command type and the command type extracting the described phonetic entry order that the described phonetic entry order obtained carries out contrasting determining that extraction obtains. Extracting corresponding phonetic entry order by capturing the mode of key word, the reliability of extraction result is high, accuracy is good.
Step S320, based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information. The command type being determined by realizes the voice display requirement of user, it is achieved mode is reliable, and treatment effeciency is high.
In one embodiment, step S320 may include that when determining that described phonetic entry order is querying command, after carrying out inquiry automatically in preset duration, directly play the information inquired about needed for current speech information with linguistic form, complete current queries order. Completing corresponding querying command by the mode automatically inquired about, search efficiency is greatly improved, and inquiry reliability can also be protected.
Wherein, the information of the required inquiry of described current speech information, including: the prestored information corresponding with described querying command and/or more fresh information; And/or, automatically inquire about in preset duration, including: multiple queries condition current speech information comprised is by the sequencing of input, after postponing the mode of preset duration successively and being sequentially completed corresponding query processing, by the querying command end rules preset, terminate current queries order. By prestoring and updating Query Information, it is possible to meet the display requirement of more multi-functional voice, be conducive to promoting Consumer's Experience and the group that extends one's service; The multiple queries order of user is realized, it is possible to ensure the reliability of inquiry, and promote the efficiency of inquiry by the mode of the inquiry of interval successively.
In one embodiment, step S320 can also include: when determining that described phonetic entry order is setting command, directly points out the currency of configuration information needed for current speech information with speech form and asks whether, with linguistic form, the expected value that needs to reset this configuration information for current speech information; Afterwards, according to user's voice feedback information in preset duration, automatically arrange in preset duration, complete current setting order; If the user while be not based on the voice feedback information of described inquiry in preset duration, then the currency giving tacit consent to described prompting is expected value, completes current setting order. By asking whether that when an order performs and terminates performing other orders, and saves the order execution time, improves order execution efficiency, hommization is good; And voice display pattern, good energy saving property is exited when not having other to perform order.
Wherein, automatically arrange in preset duration, including: what current speech information comprised multiple arranges the conditions sequencing by input, after postponing the mode of preset duration successively and being sequentially completed and arrange process accordingly, by the setting command end rules preset, terminate current setting order. Multiple setting commands of user are realized, it is possible to ensure the reliability arranged, and promote the efficiency of setting by spaced mode successively.
In step S130 place, based on described issue process obtain described in complete result, exit institute's speech commands input pattern (such as: institute's speech commands input pattern of current speech information). By, after completing the display requirement of corresponding voice, exiting current speech display operation, good energy saving property in time, also help the pattern protecting this voice operating interference-free, reduction misuse rate.
In one embodiment, after completing current described phonetic entry order, ask the user whether to need to perform other orders with speech form, and based on user's feedback of speech form in preset duration, carry out respective handling by the command type of this feedback voice; And, when not receiving user in preset duration based on the feedback of the speech form of described inquiry, automatically exit from current voice command input pattern. Determine that current speech display operation has completed and currently without, when needing the voice display operated, automatically exiting from current speech display operation, hommization is good, energy-conserving and environment-protective by voice inquiry.
Preferably, said method can also include: learnt by this locality and/or cloud computing and/or program upgrading mode, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice are carried out online upgrading and/or renewal processes, to obtain described voice packet and/or the spreading result of voice command bag and/or prestored information. By multiple data acquiring mode, realize upgrading and the renewal of prestored information, the environmental suitability of corresponding voice display operation can be promoted, and then promote the versatility of corresponding voice display operation and the popularity of user group, and then promote result of use and Consumer's Experience.
In one example, can collect and be collected locally information including at least local language, conventional term and use habit, it is collected locally after information is analyzed to described, based on analyzing result Auto-matching user and/or deleting in the institute's speech commands bag prestored untapped data in preset duration, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or, by cloud computing, the described information that is collected locally is sent to server, carry out secondary analysis by server, after secondary analysis results verification, automatically download the user based on secondary analysis result and use data; And/or, increasing up-to-date user data by cloud computing, this user data comes from network collection information and the analysis result to network collection information; To realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or, the upgrading of the program being upgraded by difference and/or normally upgrade, the described voice packet prestored and/or the institute's speech commands bag and/or the prestored information corresponding with respective voice that prestore are carried out online upgrading. By the restriction to concrete data acquiring mode and upgrading and update mode, it is possible to promote the versatility of corresponding voice display operation and the popularity of user group further.
Further, said method can also include: under institute's speech commands input pattern of described activation, and/or, based on described issue process obtain described in complete result, automatically display and/or point out the current spendable phonetic function of user with speech form. By to currently using showing in time of phonetic function with close friend, it is possible to save the time of user operation, lifting operation efficiency and Consumer's Experience.
Through substantial amounts of verification experimental verification, adopt the technical scheme of the present embodiment, that is detected the control carrying out voice command input pattern and respective voice in real time by acoustic information issues process, using phonetic entry as display interactive mode, user's dependence to traditional display modes (such as: the mode that display panel is directly operated) can be reduced, by the mode such as speech exchange, order, it is possible to achieve show function (such as: what display panel carried out directly operation shows function accordingly) accordingly or read the data of unit (such as: air conditioning unit).
According to embodiments of the invention, additionally provide a kind of display device based on speech recognition corresponding to the display packing based on speech recognition. The structural representation of one embodiment of assembly of the invention shown in Figure 4. This device at least includes: voice recognition unit 102, order issues unit 104 and pattern exits unit 106.
Wherein, voice recognition unit 102, for the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, activate voice command input pattern (such as: the voice command input pattern of current speech information). The concrete function of this voice recognition unit 102 and process are referring to step S110. By acoustic information (such as: display panel place environment space) in default environmental field is sampled and is identified, it is possible to promote reliability and the accuracy of the voice command of input; When the voice command of input meets pre-conditioned, activate corresponding voice command input pattern to realize the reliable input of voice command, good energy saving property, functional reliability is high, is conducive to promoting use quality that voice shows and extends the service life that voice shows.
In one embodiment, voice recognition unit 102, including: sound screens module 1022, voice pretreatment module 1024 and mode activation module 1026.
Wherein, sound screens module 1022, presets the acoustic information of input in environmental field for detection in real time, and when there being acoustic information to input, according to the voice packet prestored, described acoustic information is carried out examination process, to determine that whether current sound information is for voice messaging. This sound is screened the concrete function of module 1022 and processes referring to step S210. By detecting in default environmental field acoustic information (such as: display panel place environment space) in real time, processed by examination and current sound information is carried out preliminary identifying processing, mode of operation is simple, reliable, is conducive to reliability and safety that voice shows.
Wherein, according to the voice packet prestored, described acoustic information is carried out examination process, it is possible to including:
When sound reaches certain frequency (such as: acquiescence 50Hz), acquiescence has sound to input. If sound input time short (such as: estimate in 0.3s), it is believed that current sound is illegal, is not linguistic information; Otherwise, then it is assumed that current sound is voice messaging.
Wherein, voice pretreatment module 1024, for when described acoustic information is voice messaging, being sequentially carried out filtration and process with similar fractional analysis, to obtain described similar fractional analysis result to described voice messaging. The concrete function of this voice pretreatment module 1024 and process are referring to step S220. By the voice messaging determined is carried out pretreatment, to filter out the burr information in voice messaging, it is possible to promote accuracy and the reliability of the voice command of input, also help lifting user's experience.
Wherein, when described acoustic information is voice messaging, described voice messaging is sequentially carried out filtration and processes with similar fractional analysis, it is possible to including:
First, aforementioned examination is processed the sound screened, identifies that it wakes up or command statement. When the voice data translation gathered is that the treatable data of computer (such as: speech recognizer processes output data) reach more than 60% (can set) with the Data Matching degree recorded in advance, then it is assumed that current language information is effective.
Secondly, for long-time phonetic entry, inside not interrupted voice, as inputted at certain time length (such as: in 15s) invalid command, no longer receive discontinuously voice (such as: constantly continued shows that voice stopped to the speech interval time next time less than 2 seconds). Invalid voice input stopping more than 2 seconds after when re-entering voice, again identify voice.
Then, to efficient voice order, in 20 seconds after terminating such as command statement, without subsequent commands, current speech input stops.
Wherein, mode activation module 1026, for when described similar fractional analysis result meets default voice command activation condition, activating voice command input pattern (such as: the voice command input pattern of current speech information). The concrete function of this mode activation module 1026 and process are referring to step S230. Activating corresponding voice command input pattern by aforementioned processing result, safety is good, and reliability is high.
Wherein, order issues unit 104, for extracting the phonetic entry order that (such as: can extract under institute's speech commands input pattern of described activation) current speech information is carried, and issue process by default command type to extracting the described phonetic entry order that obtains, complete result with what obtain described phonetic entry order. This order issues the concrete function of unit 104 and processes referring to step S120. By, under the voice command input pattern activated, extracting voice command in the current speech information of input and perform this voice command, complete the voice display requirement of user so that reliability and motility that voice shows all are improved.
In one embodiment, order issues unit 104, including: determination type module 1042 and order complete module 1044.
Wherein, determination type module 1042, for capturing the key word of current speech information by predeterminated frequency, the voice command bag prestored based on this keyword search is to extract the phonetic entry order corresponding with current speech information, and based on default command type and the command type extracting the described phonetic entry order that the described phonetic entry order obtained carries out contrasting determining that extraction obtains. The type is determined the concrete function of module 1042 and processes referring to step S310. Extracting corresponding phonetic entry order by capturing the mode of key word, the reliability of extraction result is high, accuracy is good.
Wherein, ordered module 1044, for based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information. This order completes the concrete function of module 1044 and processes referring to step S320. The command type being determined by realizes the voice display requirement of user, it is achieved mode is reliable, and treatment effeciency is high.
Below in conjunction with the structural representation of the embodiment having ordered module in the system that Fig. 5 is the present invention, further illustrate order and complete the concrete structure of module 1044. Order module 1044, it is possible to including: querying command completes submodule 10442; Can also include: setting command completes submodule 10444.
Wherein, querying command completes submodule 10442, for when determining that described phonetic entry order is querying command, after carrying out inquiry automatically, directly playing the information inquired about needed for current speech information with linguistic form, complete current queries order in preset duration. Completing corresponding querying command by the mode automatically inquired about, search efficiency is greatly improved, and inquiry reliability can also be protected.
Wherein, the information of the required inquiry of described current speech information, including: the prestored information corresponding with described querying command and/or more fresh information. By prestoring and updating Query Information, it is possible to meet the display requirement of more multi-functional voice, be conducive to promoting Consumer's Experience and the group that extends one's service.
In one embodiment, querying command completes submodule 10442, it is possible to including: inquiry submodule 104422 automatically.
Wherein, automatically inquiry submodule 104422, for the multiple queries condition that current speech information comprised by the sequencing of input, after postponing the mode of preset duration successively and being sequentially completed corresponding query processing, by the querying command end rules preset, terminate current queries order. The multiple queries order of user is realized, it is possible to ensure the reliability of inquiry, and promote the efficiency of inquiry by the mode of the inquiry of interval successively.
Wherein, setting command completes submodule 10444, for when determining that described phonetic entry order is setting command, the currency of configuration information ask whether the expected value that needs to reset this configuration information for current speech information with linguistic form needed for directly pointing out current speech information with speech form; Afterwards, according to user's voice feedback information in preset duration, automatically arrange in preset duration, complete current setting order; If the user while be not based on the voice feedback information of described inquiry in preset duration, then the currency giving tacit consent to described prompting is expected value, completes current setting order. By asking whether that when an order performs and terminates performing other orders, and saves the order execution time, improves order execution efficiency, hommization is good; And voice display pattern, good energy saving property is exited when not having other to perform order.
In one embodiment, setting command completes submodule 10444, it is possible to including: automatically arrange submodule 104442.
Wherein, submodule is set automatically, for what current speech information comprised multiple the conditions sequencing by input is set, after postponing the mode of preset duration successively and being sequentially completed process is set accordingly, by the setting command end rules preset, terminate current setting order. Multiple setting commands of user are realized, it is possible to ensure the reliability arranged, and promote the efficiency of setting by spaced mode successively.
Wherein, pattern exits unit 106, for based on described issue process obtain described in complete result, exit institute's speech commands input pattern (such as: institute's speech commands input pattern of current speech information). This pattern exits the concrete function of unit 106 and processes referring to step S130. By, after completing the display requirement of corresponding voice, exiting current speech display operation, good energy saving property in time, also help the pattern protecting this voice operating interference-free, reduction misuse rate.
In one embodiment, pattern exits unit 106, including: continue with module 1062 and module 1064 is exited in time delay.
Wherein, continue with module 1062, after being used for current described phonetic entry order, ask the user whether to need to perform other orders with speech form, and based on user's feedback of speech form in preset duration, carry out respective handling by the command type of this feedback voice.
Wherein, module 1064 is exited in time delay, for when not receiving user in preset duration based on the feedback of the speech form of described inquiry, automatically exiting from current voice command input pattern. Determine that current speech display operation has completed and currently without, when needing the voice display operated, automatically exiting from current speech display operation, hommization is good, energy-conserving and environment-protective by voice inquiry.
Preferably, said system can also include: functional expansion unit 110.
Wherein, functional expansion unit 110, for passing through this locality study and/or cloud computing and/or the mode of program upgrading, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice are carried out online upgrading and/or renewal processes, to obtain described voice packet and/or the spreading result of voice command bag and/or prestored information. By multiple data acquiring mode, realize upgrading and the renewal of prestored information, the environmental suitability of corresponding voice display operation can be promoted, and then promote the versatility of corresponding voice display operation and the popularity of user group, and then promote result of use and Consumer's Experience.
In one example, functional expansion unit 110, including: local study module 1102 and/or cloud computing module 1104 and/or program upgraded module 1106.
Wherein, local study module 1102, it is collected locally information including at least local language, conventional term and use habit for collecting, it is collected locally after information is analyzed to described, based on analyzing result Auto-matching user and/or deleting in the institute's speech commands bag prestored untapped data in preset duration, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed.
Cloud computing module 1104, for being sent the described information that is collected locally to server by cloud computing, carries out secondary analysis by server, after secondary analysis results verification, automatically downloads the user based on secondary analysis result and uses data; And/or, increasing up-to-date user data by cloud computing, this user data comes from network collection information and the analysis result to network collection information; To realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed.
Program upgraded module 1106, for the program upgrading upgraded by difference and/or normally upgrade, carries out online upgrading to the described voice packet prestored and/or the institute's speech commands bag and/or the prestored information corresponding with respective voice that prestore.
Thus, by the restriction to concrete data acquiring mode and upgrading and update mode, it is possible to promote the versatility of corresponding voice display operation and the popularity of user group further.
Further, said system can also include: function display unit 108.
Wherein, function display unit 108, under institute's speech commands input pattern of described activation, and/or, based on described issue process obtain described in complete result, display and/or point out the current spendable phonetic function of user with speech form automatically. By to currently using showing in time of phonetic function with close friend, it is possible to save the time of user operation, lifting operation efficiency and Consumer's Experience.
The process realized due to the device of the present embodiment and function essentially correspond to the embodiment of the method shown in earlier figures 1 to Fig. 3, principle and example, therefore not detailed part in the description of the present embodiment, may refer to the related description in previous embodiment, do not repeat at this.
Through substantial amounts of verification experimental verification, adopt technical scheme, by the function of phonetic entry being extended and/or updating, (such as: by display panel auxiliary display) the relevant parameter information of the auxiliary display when voice operating or information, phonetic entry can be improved as the motility of interactive mode of display and versatility, promote Consumer's Experience further.
According to embodiments of the invention, additionally provide a kind of display system (such as: with the display panel of speech recognition, it is possible to be display panel 202) corresponding to the display packing based on speech recognition and/or the display device based on speech recognition. The structural representation of one embodiment of the system of the present invention shown in Figure 6. This display system at least includes: devices discussed above.
In one example, this display system may include that at least one display panel (such as: display panel 202), and is installed at least one control pen (such as: control pen 204) of at least one described display panel. Wherein, described display panel or control pen include devices discussed above.
Such as: controlling pen and be typically all straight cutting, position is with mould demand. Control pen and have two metal edges in the position near nib, have two effects: detect whether to be connected with display panel herein, give and control pen charging; Control the communication (power carrier) when program is upgraded. Use the purpose controlling pen to be in that to increase many a kind of operation display panel modes, thus design it is important that in order to make user better manipulate display panel to realize the control to unit.
Such as: control the function that pen can have: speech recognition; Gesture identification (utilizes gravity sensor to realize unsettled gesture); Program upgrading, language pack upgrade function; Remote control display panel function.
Such as: can controlling pen (such as: control pen 204) the upper increase of existing display panel (such as: display panel 202), the process of being particularly shown may include that
(1) by controlling pen, increase speech identifying function (such as: voice recognition unit 102) on the display panel, when display panel detection (such as: screen module 1022 by sound and detect) has sound to outside, start voice data is filtered (such as: detected by voice pretreatment module 1024), speech data is carried out similar fractional analysis (such as: carry out similar fractional analysis by voice pretreatment module 1024) again, result (such as: receive " hixxangel ") based on similar fractional analysis, activate display panel voice command input pattern (such as: mode activation module 1026).
In one example, speech identifying function is controlling realization on pen, as long as so controlling pen at hands, can control display panel either directly through voice by controlling pen; Voice relation control pen simply has input mode altogether. In mounting structure, because the control pen that is operated in of speech recognition realizes, it is necessary to assure the phonetic incepting controlling pen can receive best position at display panel sound.
Such as: during use, display panel needs controlling pen offer power supply (using during charging), it is achieved control the communication between pen and display panel. Display panel can to the process of some softwares controlling pen, for instance control prompting that pen is transferred to and insertion detects etc.
Such as: there being wifi (when can connect outer net), display panel can be communicated by wifi with when controlling the communication of pen. Here controlling pen only has network to communicate with the Distance Theory of display panel, during communication, forwarded by the server on network, and be mutually matched mutual ID when display panel powers on first with control pen, so uniquely corresponding when display panel is with the corresponding communication controlled between pen, same control pen is theoretical only can manipulate a display panel.
When without outer net wifi, control penholder in display panel, can be by power line carrier, PLC, after dial-out, display panel can be set as focus, control pen by wifi and display panel communication, but owing to display panel is as focus, control pen with display panel apart from restricted.
(2), after activating display panel voice command input pattern, display panel can be carried out order and issue (such as: order issues unit 104). Determining that command type (such as: determination type module 1042) laggard line command issues (such as: ordered module 1044), order issues time-division two class, the first kind (such as: querying command completes submodule 10442), querying command, such as " inquiry "+" Current Temperatures ", now, display panel directly plays voice. Equations of The Second Kind (such as: setting command completes submodule 10444), setting command, such as " setting "+" inflow temperature "+" 16 DEG C ", now display panel can be inquired: " current inflow temperature is xx DEG C, it is determined that resetting inflow temperature is 16 DEG C? "
(3) mutual in order to what increase with user, superincumbent order can be such that " inquiry "+" inflow temperature "+" Current Temperatures "+" xx temperature " batch query (such as: inquiry submodule 104422 automatically) or sets (such as: automatically arrange submodule 104442). Each temperature value needing inquiry postpones about 1 second, directly can terminate this order with " please " or the time of staying more than 5 seconds.
(4) after having shown order (such as: pattern exits unit 106), can inquire (such as: continue with module 1062) " also have what want I help? ", when now directly saying " not " or " thanksxxangel " or within continuous 15 seconds, do not have phonetic entry, display panel automatically exits from speech pattern (such as: module 1064 is exited in time delay).
(5) voice has the function (such as: functional expansion unit 110) such as online upgrading, language pack renewal, can connect cloud computing simultaneously, have learning functionality, can constantly accumulate the shortcut of commonly used command, learns relevant knowledge. Speech study function is mainly reflected in two places:
1. local study (such as: local study module 1102). Collect local use, collect including local language, commonly use term and use habit (such as when inquiring about set state, the reference order etc. of inquiry) etc., after collection, by analysis, Auto-matching user, experience alternately increasing user, in like manner, it is also possible to delete some long-time no data (such as common-use words), to save display panel storage resources.
Such as: because local language pack is not complete language pack, the voice module of control pen can be collected the conventional voice of part user and be dealt in cloud computer, the local dialect being found user by cloud computer and the contrast of complete language pack (contrasts the voice of the same Chinese meaning, be converted to, by voice, the valid data that computer can recognise that to compare with the data in language pack, find matching degree the highest, change with the tone of language, the immediate voice of the valid data such as frequency, judge whether to belong to this local voice), feed back this information voice module to control pen again, when ROMPaq next time, relevant local dialect bag can be downloaded. for the dialect differentiating user changed, control pen and only can collect the simple voice of the relatively good discriminating user dialect of energy, for instance, hello, you where, etc., ordinary circumstance will not collect long voice. use can also manually select suitable voice packet, now to return control penholder to display panel, be operated by display panel.
Conventional term and use habit are manageable Fuzzy processing when judging to use whether transmitting order to lower levels, if as making employment reason, when sounding sound is unintelligible, control pen can suitable Fuzzy processing to this commonly used command.
Common-use words can be done Fuzzy processing by the voice module controlling pen, if it find that certain common-use words long-time not used time, can automatically delete this common-use words.
2. cloud computing (such as: cloud computing module 1104). Part I, by cloud computing, the information being collected locally is dealt on server, more powerful server is allowed to carry out secondary analysis, after confirmation, automatically for the data of this display panel download suitable user use (such as: language pack etc., result is analyzed, for instance someone likes being to increase modal particle etc. speaking, and also having is exactly the local dialect etc.) including the use habit making employment. Part II, increasing up-to-date user data by cloud computing, this user data is generally network collection information (such as: be all collected by the voice module controlling pen, server collect, eventually for big data analysis) analyze out, different from being collected locally data.
Such as: during download, because normal language pack is all relatively completely, after server analysis, can suitably delete the data content of language pack for increase new network for or directly reduce the size of data of language pack. The secondary analysis of server, including dialect matching ratio relatively, the analysis of common-use words, and the use habit coupling of similar users, for instance some people likes increasing modal particle etc. when speaking. In order to accept this function, a server for this work can be produced, during display panel upgrading each time, be fixedly attached on this server, detected whether change simultaneously, change can be pointed out if any renewal.
Such as: during data analysis, it is possible to by manual analysis, mainly include filtering uncivil term, indivedual dialect discriminatings etc.; Server analysis can also be passed through, determine including dialect, big data analysis etc.
Part III, online upgrading (such as: program upgraded module 1106), above update for data, here upgrading for program, upgrading is divided into difference upgrading and normal upgrading, and difference upgrading can contrast the difference of version above and latest edition, carry out difference upgrading, advantage is, difference AKU is smaller, and updating speed is fast. Phonological component can all be upgraded by normal upgrading, and AKU is relatively larger, and upgrading is slow.
Such as: described program, the program of the special format of display panel or control pen it is used exclusively for. Display panel and the program controlling pen are not same, are upgrade respectively.
(6) after voice (such as: after current speech order completes), to phonetic function can be used at present to indicate (such as: function display unit 108) on display panel, such as: show a smiling face, people is glimmered at the icon talked at display panel.
The process realized due to the display system of the present embodiment and function essentially correspond to the method shown in earlier figures 1 to Fig. 3 and/or the embodiment of the device shown in Fig. 4, Fig. 5, principle and example, therefore not detailed part in the description of the present embodiment, may refer to the related description in previous embodiment, do not repeat at this.
Through substantial amounts of verification experimental verification, adopt technical scheme, by the use of phonetic entry, it is possible to reduce user's dependence to display panel, during operation, it is not necessary to directly operate display panel; By the mode such as speech exchange, order, display panel can be operated or reads the data of unit (such as: air conditioning unit), it is thus possible to by extending tradition display panel interactive function, provide the user with the interactive mode that a kind of tradition display panel is brand-new. Wherein, during voice operating, display panel can assist display relevant parameter information or information, it is possible to improves motility and versatility that display panel uses, promotes result of use and the Consumer's Experience of display panel further.
According to embodiments of the invention, additionally provide a kind of air-conditioning corresponding to the display packing based on speech recognition and/or the display system based on speech recognition and/or display system. This air-conditioning at least includes: above-described display system.
The process realized due to the air-conditioning of the present embodiment and function essentially correspond to the method shown in earlier figures 1 to Fig. 3 and/or the device shown in Fig. 4, Fig. 5 and/or the embodiment of the display system shown in Fig. 6, principle and example, therefore not detailed part in the description of the present embodiment, may refer to the related description in previous embodiment, do not repeat at this.
Through substantial amounts of verification experimental verification, adopt technical scheme, detected in real time by acoustic information, the voice command input pattern of air-conditioning is controlled and respective voice issue process, using phonetic entry as between air-conditioning and user display interactive mode, user's dependence to direct operating air conditioner display panel can be reduced, improve motility and versatility that the air-conditioner display panel uses, and then promote result of use and the Consumer's Experience of air-conditioning.
It can further be stated that, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include the process of a series of key element, method, commodity or equipment not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, commodity or equipment. When there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, commodity or equipment.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program. Therefore, the present invention can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect. And, the present invention can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code.
The foregoing is only embodiments of the invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations. All within the spirit and principles in the present invention, any amendment of making, equivalent replacement, improvement etc., should be included within scope of the presently claimed invention.
Claims (24)
1. the display packing based on speech recognition, it is characterised in that including:
The acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, activates voice command input pattern;
Extract the phonetic entry order carried of current speech information, and issue process by default command type to extracting the described phonetic entry order obtained, complete result with what obtain described phonetic entry order; And
Based on described issue process obtain described in complete result, exit institute's speech commands input pattern.
2. method according to claim 1, it is characterised in that the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, to activate voice command input pattern, including:
The acoustic information of input in environmental field is preset in detection in real time, and when there being acoustic information to input, according to the voice packet prestored, described acoustic information is carried out examination process, to determine that whether current sound information is for voice messaging;
When described acoustic information is voice messaging, described voice messaging is sequentially carried out filtration and processes with similar fractional analysis, to obtain described similar fractional analysis result;
When described similar fractional analysis result meets default voice command activation condition, activate voice command input pattern.
3. method according to claim 1 and 2, it is characterised in that extract the phonetic entry order that current speech information is carried, and issue process by default command type to extracting the described phonetic entry order obtained, including:
The key word of current speech information is captured by predeterminated frequency, the voice command bag prestored based on this keyword search is to extract the phonetic entry order corresponding with current speech information, and based on default command type and the command type extracting the described phonetic entry order that the described phonetic entry order obtained carries out contrasting determining that extraction obtains;
Based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information.
4. method according to claim 3, it is characterised in that based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information, including:
When determining that described phonetic entry order is querying command, after carrying out inquiry automatically in preset duration, directly play the information inquired about needed for current speech information with linguistic form, complete current queries order.
5. method according to claim 4, it is characterised in that
The information of the required inquiry of described current speech information, including: the prestored information corresponding with described querying command and/or more fresh information;
And/or,
Automatically inquire about in preset duration, including:
Multiple queries condition current speech information comprised is by the sequencing of input, after postponing the mode of preset duration successively and being sequentially completed corresponding query processing, by the querying command end rules preset, terminates current queries order.
6. according to the method one of claim 3-5 Suo Shu, it is characterised in that based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information, also includes:
When determining that described phonetic entry order is setting command, directly point out the currency of configuration information needed for current speech information with speech form and ask whether, with linguistic form, the expected value that needs to reset this configuration information for current speech information; Afterwards,
According to user's voice feedback information in preset duration, automatically arrange in preset duration, complete current setting order;
If the user while be not based on the voice feedback information of described inquiry in preset duration, then the currency giving tacit consent to described prompting is expected value, completes current setting order.
7. method according to claim 6, it is characterised in that automatically arrange in preset duration, including:
What current speech information comprised multiple arranges the conditions sequencing by input, after postponing the mode of preset duration successively and being sequentially completed and arrange process accordingly, by the setting command end rules preset, terminates current setting order.
8. according to the method one of claim 1-7 Suo Shu, it is characterised in that based on described issue process obtain described in complete result, exit institute's speech commands input pattern of current speech information, including:
After completing current described phonetic entry order, ask the user whether to need to perform other orders with speech form, and based on user's feedback of speech form in preset duration, carry out respective handling by the command type of this feedback voice; And,
When not receiving user in preset duration based on the feedback of the speech form of described inquiry, automatically exit from current voice command input pattern.
9. according to the method one of claim 2-8 Suo Shu, it is characterised in that the method also includes:
Learnt by this locality and/or cloud computing and/or program upgrading mode, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice are carried out online upgrading and/or renewal processes, to obtain described voice packet and/or the spreading result of voice command bag and/or prestored information.
10. method according to claim 9, it is characterized in that, learnt by this locality and/or cloud computing and/or program upgrading mode, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice carry out online upgrading and/or renewal processes, including:
Collection is collected locally information including at least local language, conventional term and use habit, it is collected locally after information is analyzed to described, based on analyzing result Auto-matching user and/or deleting in the institute's speech commands bag prestored untapped data in preset duration, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or,
By cloud computing, the described information that is collected locally is sent to server, carry out secondary analysis by server, after secondary analysis results verification, automatically download the user based on secondary analysis result and use data; And/or, increasing up-to-date user data by cloud computing, this user data comes from network collection information and the analysis result to network collection information; To realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or,
The program upgrading upgraded by difference and/or normally upgrade, carries out online upgrading to the described voice packet prestored and/or the institute's speech commands bag and/or the prestored information corresponding with respective voice that prestore.
11. according to the method one of claim 1-10 Suo Shu, it is characterised in that the method also includes:
Under institute's speech commands input pattern of described activation, and/or, based on described issue process obtain described in complete result, automatically display and/or point out the current spendable phonetic function of user with speech form.
12. the display device based on speech recognition, it is characterised in that including:
Voice recognition unit, for the acoustic information of input in default environmental field is carried out voice recognition processing, when determining that current sound information is voice messaging, activates voice command input pattern;
Order issues unit, extract phonetic entry order that current speech information carries, and issue process by default command type to extracting the described phonetic entry order obtained, complete result with what obtain described phonetic entry order; And
Pattern exits unit, for based on described issue process obtain described in complete result, exit institute's speech commands input pattern.
13. device according to claim 12, it is characterised in that voice recognition unit, including:
Sound screens module, presets the acoustic information of input in environmental field for detection in real time, and when there being acoustic information to input, according to the voice packet prestored, described acoustic information is carried out examination process, to determine that whether current sound information is for voice messaging;
Voice pretreatment module, for when described acoustic information is voice messaging, being sequentially carried out filtration and process with similar fractional analysis, to obtain described similar fractional analysis result to described voice messaging;
Mode activation module, for when described similar fractional analysis result meets default voice command activation condition, activating voice command input pattern.
14. the device according to claim 12 or 13, it is characterised in that order issues unit, including:
Determination type module, for capturing the key word of current speech information by predeterminated frequency, the voice command bag prestored based on this keyword search is to extract the phonetic entry order corresponding with current speech information, and based on default command type and the command type extracting the described phonetic entry order that the described phonetic entry order obtained carries out contrasting determining that extraction obtains;
Ordered module, for based on a determination that described command type, described phonetic entry order is issued process, to complete the described phonetic entry order of current speech information.
15. device according to claim 14, it is characterised in that ordered module, including:
Querying command completes submodule, for when determining that described phonetic entry order is querying command, after carrying out inquiry automatically, directly playing the information inquired about needed for current speech information with linguistic form, complete current queries order in preset duration.
16. device according to claim 15, it is characterised in that
The information of the required inquiry of described current speech information, including: the prestored information corresponding with described querying command and/or more fresh information;
And/or,
Querying command completes submodule, including:
Automatically submodule is inquired about, for sequencing by input of multiple queries condition that current speech information is comprised, after postponing the mode of preset duration successively and being sequentially completed corresponding query processing, by the querying command end rules preset, terminate current queries order.
17. according to the device one of claim 14-16 Suo Shu, it is characterised in that ordered module, also include:
Setting command completes submodule, for when determining that described phonetic entry order is setting command, the currency of configuration information ask whether the expected value that needs to reset this configuration information for current speech information with linguistic form needed for directly pointing out current speech information with speech form; Afterwards,
According to user's voice feedback information in preset duration, automatically arrange in preset duration, complete current setting order;
If the user while be not based on the voice feedback information of described inquiry in preset duration, then the currency giving tacit consent to described prompting is expected value, completes current setting order.
18. device according to claim 17, it is characterised in that setting command completes submodule, including:
Submodule is set automatically, for current speech information is comprised multiple arrange conditions by input sequencing, after postponing the mode of preset duration successively and being sequentially completed process is set accordingly, by the setting command end rules preset, terminate current setting order.
19. according to the device one of claim 12-18 Suo Shu, it is characterised in that pattern exits unit, including:
Continue with module, after being used for current described phonetic entry order, ask the user whether to need to perform other orders with speech form, and based on user's feedback of speech form in preset duration, carry out respective handling by the command type of this feedback voice; And,
Module is exited in time delay, for when not receiving user in preset duration based on the feedback of the speech form of described inquiry, automatically exiting from current voice command input pattern.
20. according to the device one of claim 13-19 Suo Shu, it is characterised in that this system also includes:
Functional expansion unit, for passing through this locality study and/or cloud computing and/or the mode of program upgrading, the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice are carried out online upgrading and/or renewal processes, to obtain described voice packet and/or the spreading result of voice command bag and/or prestored information.
21. device according to claim 20, it is characterised in that functional expansion unit, including:
Local study module, it is collected locally information including at least local language, conventional term and use habit for collecting, it is collected locally after information is analyzed to described, based on analyzing result Auto-matching user and/or deleting in the institute's speech commands bag prestored untapped data in preset duration, to realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or,
Cloud computing module, for being sent the described information that is collected locally to server by cloud computing, carries out secondary analysis by server, after secondary analysis results verification, automatically downloads the user based on secondary analysis result and uses data; And/or, increasing up-to-date user data by cloud computing, this user data comes from network collection information and the analysis result to network collection information; To realize the renewal of the described voice packet prestored and/or the institute's speech commands bag prestored and/or the prestored information corresponding with respective voice is processed; And/or,
Program upgraded module, for the program upgrading upgraded by difference and/or normally upgrade, carries out online upgrading to the described voice packet prestored and/or the institute's speech commands bag and/or the prestored information corresponding with respective voice that prestore.
22. according to the device one of claim 12-21 Suo Shu, it is characterised in that this device also includes:
Function display unit, under institute's speech commands input pattern of described activation, and/or, based on described issue process obtain described in complete result, display and/or point out the current spendable phonetic function of user with speech form automatically.
23. a display system, it is characterised in that include as arbitrary in claim 12-22 as described in device.
24. an air-conditioning, it is characterised in that there is display system as claimed in claim 23.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510993344.1A CN105679318A (en) | 2015-12-23 | 2015-12-23 | Display method and device based on voice recognition, display system and air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510993344.1A CN105679318A (en) | 2015-12-23 | 2015-12-23 | Display method and device based on voice recognition, display system and air conditioner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105679318A true CN105679318A (en) | 2016-06-15 |
Family
ID=56297716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510993344.1A Pending CN105679318A (en) | 2015-12-23 | 2015-12-23 | Display method and device based on voice recognition, display system and air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105679318A (en) |
Cited By (73)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037962A (en) * | 2017-12-11 | 2018-05-15 | 深圳市沃特沃德股份有限公司 | System method to set up and device |
| CN108257616A (en) * | 2017-12-05 | 2018-07-06 | 苏州车萝卜汽车电子科技有限公司 | Interactive detection method and device |
| WO2018161473A1 (en) * | 2017-03-09 | 2018-09-13 | 广东美的制冷设备有限公司 | Voice control method and device, and air conditioner |
| CN108592301A (en) * | 2018-04-28 | 2018-09-28 | 四川虹美智能科技有限公司 | A kind of acoustic control intelligent air-conditioning, system and application method |
| CN108758989A (en) * | 2018-04-28 | 2018-11-06 | 四川虹美智能科技有限公司 | A kind of air-conditioning and its application method |
| CN108766460A (en) * | 2018-05-15 | 2018-11-06 | 浙江口碑网络技术有限公司 | Voice-based exchange method and system |
| CN109495360A (en) * | 2018-12-18 | 2019-03-19 | 深圳国美云智科技有限公司 | A kind of smart home Internet of Things platform, offline sound control method and system |
| CN109493856A (en) * | 2017-09-12 | 2019-03-19 | 合肥美的智能科技有限公司 | Identify method and apparatus, household electrical appliance and the machine readable storage medium of voice |
| CN109523998A (en) * | 2018-11-06 | 2019-03-26 | 珠海格力电器股份有限公司 | Voice command refined display system and method and intelligent terminal |
| CN109637533A (en) * | 2018-12-25 | 2019-04-16 | 深圳市道通智能航空技术有限公司 | Unmanned vehicle, its voice system and voice interactive method |
| CN109710796A (en) * | 2019-01-14 | 2019-05-03 | Oppo广东移动通信有限公司 | Voice-based image search method, device, storage medium and terminal |
| CN109976702A (en) * | 2019-03-20 | 2019-07-05 | 青岛海信电器股份有限公司 | A kind of audio recognition method, device and terminal |
| CN110073326A (en) * | 2016-10-19 | 2019-07-30 | 搜诺思公司 | Speech recognition based on arbitration |
| CN110235561A (en) * | 2019-06-24 | 2019-09-17 | 厦门钛尚人工智能科技有限公司 | A kind of reading intelligent agriculture seeder |
| CN110265017A (en) * | 2019-06-27 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | Method of speech processing and device |
| CN111316226A (en) * | 2017-11-10 | 2020-06-19 | 三星电子株式会社 | Electronic device and control method thereof |
| CN112652303A (en) * | 2020-08-23 | 2021-04-13 | 广州市昇博电子科技有限公司 | Local engine voice recognition and interaction method |
| US11343614B2 (en) | 2018-01-31 | 2022-05-24 | Sonos, Inc. | Device designation of playback and network microphone device arrangements |
| US11405430B2 (en) | 2016-02-22 | 2022-08-02 | Sonos, Inc. | Networked microphone device control |
| US11482978B2 (en) | 2018-08-28 | 2022-10-25 | Sonos, Inc. | Audio notifications |
| US11482224B2 (en) | 2020-05-20 | 2022-10-25 | Sonos, Inc. | Command keywords with input detection windowing |
| US11501773B2 (en) | 2019-06-12 | 2022-11-15 | Sonos, Inc. | Network microphone device with command keyword conditioning |
| US11500611B2 (en) | 2017-09-08 | 2022-11-15 | Sonos, Inc. | Dynamic computation of system response volume |
| US11514898B2 (en) | 2016-02-22 | 2022-11-29 | Sonos, Inc. | Voice control of a media playback system |
| US11531520B2 (en) | 2016-08-05 | 2022-12-20 | Sonos, Inc. | Playback device supporting concurrent voice assistants |
| US11538460B2 (en) | 2018-12-13 | 2022-12-27 | Sonos, Inc. | Networked microphone devices, systems, and methods of localized arbitration |
| US11538451B2 (en) | 2017-09-28 | 2022-12-27 | Sonos, Inc. | Multi-channel acoustic echo cancellation |
| US11540047B2 (en) | 2018-12-20 | 2022-12-27 | Sonos, Inc. | Optimization of network microphone devices using noise classification |
| US11545169B2 (en) | 2016-06-09 | 2023-01-03 | Sonos, Inc. | Dynamic player selection for audio signal processing |
| US11556306B2 (en) | 2016-02-22 | 2023-01-17 | Sonos, Inc. | Voice controlled media playback system |
| US11557294B2 (en) | 2018-12-07 | 2023-01-17 | Sonos, Inc. | Systems and methods of operating media playback systems having multiple voice assistant services |
| US11562740B2 (en) | 2020-01-07 | 2023-01-24 | Sonos, Inc. | Voice verification for media playback |
| US11563842B2 (en) | 2018-08-28 | 2023-01-24 | Sonos, Inc. | Do not disturb feature for audio notifications |
| US11641559B2 (en) | 2016-09-27 | 2023-05-02 | Sonos, Inc. | Audio playback settings for voice interaction |
| US11646023B2 (en) | 2019-02-08 | 2023-05-09 | Sonos, Inc. | Devices, systems, and methods for distributed voice processing |
| US11646045B2 (en) | 2017-09-27 | 2023-05-09 | Sonos, Inc. | Robust short-time fourier transform acoustic echo cancellation during audio playback |
| US11694689B2 (en) | 2020-05-20 | 2023-07-04 | Sonos, Inc. | Input detection windowing |
| US11696074B2 (en) | 2018-06-28 | 2023-07-04 | Sonos, Inc. | Systems and methods for associating playback devices with voice assistant services |
| US11698771B2 (en) | 2020-08-25 | 2023-07-11 | Sonos, Inc. | Vocal guidance engines for playback devices |
| US11710487B2 (en) | 2019-07-31 | 2023-07-25 | Sonos, Inc. | Locally distributed keyword detection |
| US11714600B2 (en) | 2019-07-31 | 2023-08-01 | Sonos, Inc. | Noise classification for event detection |
| US11736860B2 (en) | 2016-02-22 | 2023-08-22 | Sonos, Inc. | Voice control of a media playback system |
| US11741948B2 (en) | 2018-11-15 | 2023-08-29 | Sonos Vox France Sas | Dilated convolutions and gating for efficient keyword spotting |
| US11769505B2 (en) | 2017-09-28 | 2023-09-26 | Sonos, Inc. | Echo of tone interferance cancellation using two acoustic echo cancellers |
| US11778259B2 (en) | 2018-09-14 | 2023-10-03 | Sonos, Inc. | Networked devices, systems and methods for associating playback devices based on sound codes |
| US11792590B2 (en) | 2018-05-25 | 2023-10-17 | Sonos, Inc. | Determining and adapting to changes in microphone performance of playback devices |
| US11790911B2 (en) | 2018-09-28 | 2023-10-17 | Sonos, Inc. | Systems and methods for selective wake word detection using neural network models |
| US11790937B2 (en) | 2018-09-21 | 2023-10-17 | Sonos, Inc. | Voice detection optimization using sound metadata |
| US11798553B2 (en) | 2019-05-03 | 2023-10-24 | Sonos, Inc. | Voice assistant persistence across multiple network microphone devices |
| US11797263B2 (en) | 2018-05-10 | 2023-10-24 | Sonos, Inc. | Systems and methods for voice-assisted media content selection |
| US11854547B2 (en) | 2019-06-12 | 2023-12-26 | Sonos, Inc. | Network microphone device with command keyword eventing |
| US11862161B2 (en) | 2019-10-22 | 2024-01-02 | Sonos, Inc. | VAS toggle based on device orientation |
| US11869503B2 (en) | 2019-12-20 | 2024-01-09 | Sonos, Inc. | Offline voice control |
| US11893308B2 (en) | 2017-09-29 | 2024-02-06 | Sonos, Inc. | Media playback system with concurrent voice assistance |
| US11900937B2 (en) | 2017-08-07 | 2024-02-13 | Sonos, Inc. | Wake-word detection suppression |
| US11899519B2 (en) | 2018-10-23 | 2024-02-13 | Sonos, Inc. | Multiple stage network microphone device with reduced power consumption and processing load |
| US11947870B2 (en) | 2016-02-22 | 2024-04-02 | Sonos, Inc. | Audio response playback |
| US11961519B2 (en) | 2020-02-07 | 2024-04-16 | Sonos, Inc. | Localized wakeword verification |
| US11979960B2 (en) | 2016-07-15 | 2024-05-07 | Sonos, Inc. | Contextualization of voice inputs |
| US11983463B2 (en) | 2016-02-22 | 2024-05-14 | Sonos, Inc. | Metadata exchange involving a networked playback system and a networked microphone system |
| US11984123B2 (en) | 2020-11-12 | 2024-05-14 | Sonos, Inc. | Network device interaction by range |
| US12047753B1 (en) | 2017-09-28 | 2024-07-23 | Sonos, Inc. | Three-dimensional beam forming with a microphone array |
| US12062383B2 (en) | 2018-09-29 | 2024-08-13 | Sonos, Inc. | Linear filtering for noise-suppressed speech detection via multiple network microphone devices |
| US12118273B2 (en) | 2020-01-31 | 2024-10-15 | Sonos, Inc. | Local voice data processing |
| US12154569B2 (en) | 2017-12-11 | 2024-11-26 | Sonos, Inc. | Home graph |
| US12165651B2 (en) | 2018-09-25 | 2024-12-10 | Sonos, Inc. | Voice detection optimization based on selected voice assistant service |
| US12211490B2 (en) | 2019-07-31 | 2025-01-28 | Sonos, Inc. | Locally distributed keyword detection |
| US12212945B2 (en) | 2017-12-10 | 2025-01-28 | Sonos, Inc. | Network microphone devices with automatic do not disturb actuation capabilities |
| US12217748B2 (en) | 2017-03-27 | 2025-02-04 | Sonos, Inc. | Systems and methods of multiple voice services |
| US12283269B2 (en) | 2020-10-16 | 2025-04-22 | Sonos, Inc. | Intent inference in audiovisual communication sessions |
| US12327556B2 (en) | 2021-09-30 | 2025-06-10 | Sonos, Inc. | Enabling and disabling microphones and voice assistants |
| US12327549B2 (en) | 2022-02-09 | 2025-06-10 | Sonos, Inc. | Gatekeeping for voice intent processing |
| US12387716B2 (en) | 2020-06-08 | 2025-08-12 | Sonos, Inc. | Wakewordless voice quickstarts |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101292282A (en) * | 2005-08-29 | 2008-10-22 | 沃伊斯博克斯科技公司 | Mobile system and method supporting natural language man-machine interaction |
| CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
| CN103366740A (en) * | 2012-03-27 | 2013-10-23 | 联想(北京)有限公司 | Voice command recognition method and voice command recognition device |
| CN203336703U (en) * | 2013-01-31 | 2013-12-11 | 福州斯狄渢电热水器有限公司 | Heating control system with voice control function |
| US20140244255A1 (en) * | 2013-02-25 | 2014-08-28 | Seiko Epson Corporation | Speech recognition device and method, and semiconductor integrated circuit device |
| CN104509079A (en) * | 2012-08-01 | 2015-04-08 | 谷歌公司 | Speech recognition models based on location indicia |
| CN105009203A (en) * | 2013-03-12 | 2015-10-28 | 纽昂斯通讯公司 | Methods and apparatus for detecting a voice command |
-
2015
- 2015-12-23 CN CN201510993344.1A patent/CN105679318A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101292282A (en) * | 2005-08-29 | 2008-10-22 | 沃伊斯博克斯科技公司 | Mobile system and method supporting natural language man-machine interaction |
| CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
| CN103366740A (en) * | 2012-03-27 | 2013-10-23 | 联想(北京)有限公司 | Voice command recognition method and voice command recognition device |
| CN104509079A (en) * | 2012-08-01 | 2015-04-08 | 谷歌公司 | Speech recognition models based on location indicia |
| CN203336703U (en) * | 2013-01-31 | 2013-12-11 | 福州斯狄渢电热水器有限公司 | Heating control system with voice control function |
| US20140244255A1 (en) * | 2013-02-25 | 2014-08-28 | Seiko Epson Corporation | Speech recognition device and method, and semiconductor integrated circuit device |
| CN105009203A (en) * | 2013-03-12 | 2015-10-28 | 纽昂斯通讯公司 | Methods and apparatus for detecting a voice command |
Cited By (91)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11832068B2 (en) | 2016-02-22 | 2023-11-28 | Sonos, Inc. | Music service selection |
| US11863593B2 (en) | 2016-02-22 | 2024-01-02 | Sonos, Inc. | Networked microphone device control |
| US11983463B2 (en) | 2016-02-22 | 2024-05-14 | Sonos, Inc. | Metadata exchange involving a networked playback system and a networked microphone system |
| US11750969B2 (en) | 2016-02-22 | 2023-09-05 | Sonos, Inc. | Default playback device designation |
| US11736860B2 (en) | 2016-02-22 | 2023-08-22 | Sonos, Inc. | Voice control of a media playback system |
| US11405430B2 (en) | 2016-02-22 | 2022-08-02 | Sonos, Inc. | Networked microphone device control |
| US11514898B2 (en) | 2016-02-22 | 2022-11-29 | Sonos, Inc. | Voice control of a media playback system |
| US12277368B2 (en) | 2016-02-22 | 2025-04-15 | Sonos, Inc. | Handling of loss of pairing between networked devices |
| US11556306B2 (en) | 2016-02-22 | 2023-01-17 | Sonos, Inc. | Voice controlled media playback system |
| US12047752B2 (en) | 2016-02-22 | 2024-07-23 | Sonos, Inc. | Content mixing |
| US11947870B2 (en) | 2016-02-22 | 2024-04-02 | Sonos, Inc. | Audio response playback |
| US11545169B2 (en) | 2016-06-09 | 2023-01-03 | Sonos, Inc. | Dynamic player selection for audio signal processing |
| US11979960B2 (en) | 2016-07-15 | 2024-05-07 | Sonos, Inc. | Contextualization of voice inputs |
| US11531520B2 (en) | 2016-08-05 | 2022-12-20 | Sonos, Inc. | Playback device supporting concurrent voice assistants |
| US11641559B2 (en) | 2016-09-27 | 2023-05-02 | Sonos, Inc. | Audio playback settings for voice interaction |
| US11727933B2 (en) | 2016-10-19 | 2023-08-15 | Sonos, Inc. | Arbitration-based voice recognition |
| CN110073326A (en) * | 2016-10-19 | 2019-07-30 | 搜诺思公司 | Speech recognition based on arbitration |
| US11308961B2 (en) | 2016-10-19 | 2022-04-19 | Sonos, Inc. | Arbitration-based voice recognition |
| WO2018161473A1 (en) * | 2017-03-09 | 2018-09-13 | 广东美的制冷设备有限公司 | Voice control method and device, and air conditioner |
| US12217748B2 (en) | 2017-03-27 | 2025-02-04 | Sonos, Inc. | Systems and methods of multiple voice services |
| US11900937B2 (en) | 2017-08-07 | 2024-02-13 | Sonos, Inc. | Wake-word detection suppression |
| US11500611B2 (en) | 2017-09-08 | 2022-11-15 | Sonos, Inc. | Dynamic computation of system response volume |
| CN109493856A (en) * | 2017-09-12 | 2019-03-19 | 合肥美的智能科技有限公司 | Identify method and apparatus, household electrical appliance and the machine readable storage medium of voice |
| US11646045B2 (en) | 2017-09-27 | 2023-05-09 | Sonos, Inc. | Robust short-time fourier transform acoustic echo cancellation during audio playback |
| US11538451B2 (en) | 2017-09-28 | 2022-12-27 | Sonos, Inc. | Multi-channel acoustic echo cancellation |
| US12047753B1 (en) | 2017-09-28 | 2024-07-23 | Sonos, Inc. | Three-dimensional beam forming with a microphone array |
| US12236932B2 (en) | 2017-09-28 | 2025-02-25 | Sonos, Inc. | Multi-channel acoustic echo cancellation |
| US11769505B2 (en) | 2017-09-28 | 2023-09-26 | Sonos, Inc. | Echo of tone interferance cancellation using two acoustic echo cancellers |
| US11893308B2 (en) | 2017-09-29 | 2024-02-06 | Sonos, Inc. | Media playback system with concurrent voice assistance |
| CN111316226B (en) * | 2017-11-10 | 2024-01-12 | 三星电子株式会社 | Electronic device and control method thereof |
| CN111316226A (en) * | 2017-11-10 | 2020-06-19 | 三星电子株式会社 | Electronic device and control method thereof |
| CN108257616A (en) * | 2017-12-05 | 2018-07-06 | 苏州车萝卜汽车电子科技有限公司 | Interactive detection method and device |
| US12212945B2 (en) | 2017-12-10 | 2025-01-28 | Sonos, Inc. | Network microphone devices with automatic do not disturb actuation capabilities |
| US12154569B2 (en) | 2017-12-11 | 2024-11-26 | Sonos, Inc. | Home graph |
| CN108037962A (en) * | 2017-12-11 | 2018-05-15 | 深圳市沃特沃德股份有限公司 | System method to set up and device |
| US11689858B2 (en) | 2018-01-31 | 2023-06-27 | Sonos, Inc. | Device designation of playback and network microphone device arrangements |
| US11343614B2 (en) | 2018-01-31 | 2022-05-24 | Sonos, Inc. | Device designation of playback and network microphone device arrangements |
| CN108758989A (en) * | 2018-04-28 | 2018-11-06 | 四川虹美智能科技有限公司 | A kind of air-conditioning and its application method |
| CN108592301A (en) * | 2018-04-28 | 2018-09-28 | 四川虹美智能科技有限公司 | A kind of acoustic control intelligent air-conditioning, system and application method |
| US11797263B2 (en) | 2018-05-10 | 2023-10-24 | Sonos, Inc. | Systems and methods for voice-assisted media content selection |
| US12360734B2 (en) | 2018-05-10 | 2025-07-15 | Sonos, Inc. | Systems and methods for voice-assisted media content selection |
| CN108766460A (en) * | 2018-05-15 | 2018-11-06 | 浙江口碑网络技术有限公司 | Voice-based exchange method and system |
| US11792590B2 (en) | 2018-05-25 | 2023-10-17 | Sonos, Inc. | Determining and adapting to changes in microphone performance of playback devices |
| US11696074B2 (en) | 2018-06-28 | 2023-07-04 | Sonos, Inc. | Systems and methods for associating playback devices with voice assistant services |
| US11563842B2 (en) | 2018-08-28 | 2023-01-24 | Sonos, Inc. | Do not disturb feature for audio notifications |
| US11482978B2 (en) | 2018-08-28 | 2022-10-25 | Sonos, Inc. | Audio notifications |
| US11778259B2 (en) | 2018-09-14 | 2023-10-03 | Sonos, Inc. | Networked devices, systems and methods for associating playback devices based on sound codes |
| US11790937B2 (en) | 2018-09-21 | 2023-10-17 | Sonos, Inc. | Voice detection optimization using sound metadata |
| US12230291B2 (en) | 2018-09-21 | 2025-02-18 | Sonos, Inc. | Voice detection optimization using sound metadata |
| US12165651B2 (en) | 2018-09-25 | 2024-12-10 | Sonos, Inc. | Voice detection optimization based on selected voice assistant service |
| US12165644B2 (en) | 2018-09-28 | 2024-12-10 | Sonos, Inc. | Systems and methods for selective wake word detection |
| US11790911B2 (en) | 2018-09-28 | 2023-10-17 | Sonos, Inc. | Systems and methods for selective wake word detection using neural network models |
| US12062383B2 (en) | 2018-09-29 | 2024-08-13 | Sonos, Inc. | Linear filtering for noise-suppressed speech detection via multiple network microphone devices |
| US11899519B2 (en) | 2018-10-23 | 2024-02-13 | Sonos, Inc. | Multiple stage network microphone device with reduced power consumption and processing load |
| CN109523998A (en) * | 2018-11-06 | 2019-03-26 | 珠海格力电器股份有限公司 | Voice command refined display system and method and intelligent terminal |
| US11741948B2 (en) | 2018-11-15 | 2023-08-29 | Sonos Vox France Sas | Dilated convolutions and gating for efficient keyword spotting |
| US11557294B2 (en) | 2018-12-07 | 2023-01-17 | Sonos, Inc. | Systems and methods of operating media playback systems having multiple voice assistant services |
| US11538460B2 (en) | 2018-12-13 | 2022-12-27 | Sonos, Inc. | Networked microphone devices, systems, and methods of localized arbitration |
| CN109495360A (en) * | 2018-12-18 | 2019-03-19 | 深圳国美云智科技有限公司 | A kind of smart home Internet of Things platform, offline sound control method and system |
| US11540047B2 (en) | 2018-12-20 | 2022-12-27 | Sonos, Inc. | Optimization of network microphone devices using noise classification |
| CN109637533A (en) * | 2018-12-25 | 2019-04-16 | 深圳市道通智能航空技术有限公司 | Unmanned vehicle, its voice system and voice interactive method |
| CN109710796A (en) * | 2019-01-14 | 2019-05-03 | Oppo广东移动通信有限公司 | Voice-based image search method, device, storage medium and terminal |
| US11646023B2 (en) | 2019-02-08 | 2023-05-09 | Sonos, Inc. | Devices, systems, and methods for distributed voice processing |
| CN109976702A (en) * | 2019-03-20 | 2019-07-05 | 青岛海信电器股份有限公司 | A kind of audio recognition method, device and terminal |
| US11798553B2 (en) | 2019-05-03 | 2023-10-24 | Sonos, Inc. | Voice assistant persistence across multiple network microphone devices |
| US11501773B2 (en) | 2019-06-12 | 2022-11-15 | Sonos, Inc. | Network microphone device with command keyword conditioning |
| US11854547B2 (en) | 2019-06-12 | 2023-12-26 | Sonos, Inc. | Network microphone device with command keyword eventing |
| CN110235561B (en) * | 2019-06-24 | 2021-03-26 | 厦门钛尚人工智能科技有限公司 | Seeder for intelligent agriculture |
| CN110235561A (en) * | 2019-06-24 | 2019-09-17 | 厦门钛尚人工智能科技有限公司 | A kind of reading intelligent agriculture seeder |
| CN110265017B (en) * | 2019-06-27 | 2021-08-17 | 百度在线网络技术（北京）有限公司 | Voice processing method and device |
| US11164583B2 (en) | 2019-06-27 | 2021-11-02 | Baidu Online Network Technology (Beijing) Co., Ltd. | Voice processing method and apparatus |
| CN110265017A (en) * | 2019-06-27 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | Method of speech processing and device |
| US12211490B2 (en) | 2019-07-31 | 2025-01-28 | Sonos, Inc. | Locally distributed keyword detection |
| US11714600B2 (en) | 2019-07-31 | 2023-08-01 | Sonos, Inc. | Noise classification for event detection |
| US11710487B2 (en) | 2019-07-31 | 2023-07-25 | Sonos, Inc. | Locally distributed keyword detection |
| US11862161B2 (en) | 2019-10-22 | 2024-01-02 | Sonos, Inc. | VAS toggle based on device orientation |
| US11869503B2 (en) | 2019-12-20 | 2024-01-09 | Sonos, Inc. | Offline voice control |
| US11562740B2 (en) | 2020-01-07 | 2023-01-24 | Sonos, Inc. | Voice verification for media playback |
| US12118273B2 (en) | 2020-01-31 | 2024-10-15 | Sonos, Inc. | Local voice data processing |
| US11961519B2 (en) | 2020-02-07 | 2024-04-16 | Sonos, Inc. | Localized wakeword verification |
| US11482224B2 (en) | 2020-05-20 | 2022-10-25 | Sonos, Inc. | Command keywords with input detection windowing |
| US11694689B2 (en) | 2020-05-20 | 2023-07-04 | Sonos, Inc. | Input detection windowing |
| US12387716B2 (en) | 2020-06-08 | 2025-08-12 | Sonos, Inc. | Wakewordless voice quickstarts |
| CN112652303A (en) * | 2020-08-23 | 2021-04-13 | 广州市昇博电子科技有限公司 | Local engine voice recognition and interaction method |
| CN112652303B (en) * | 2020-08-23 | 2024-10-11 | 广州市昇博电子科技有限公司 | Local engine voice recognition and interaction method |
| US11698771B2 (en) | 2020-08-25 | 2023-07-11 | Sonos, Inc. | Vocal guidance engines for playback devices |
| US12283269B2 (en) | 2020-10-16 | 2025-04-22 | Sonos, Inc. | Intent inference in audiovisual communication sessions |
| US11984123B2 (en) | 2020-11-12 | 2024-05-14 | Sonos, Inc. | Network device interaction by range |
| US12424220B2 (en) | 2020-11-12 | 2025-09-23 | Sonos, Inc. | Network device interaction by range |
| US12327556B2 (en) | 2021-09-30 | 2025-06-10 | Sonos, Inc. | Enabling and disabling microphones and voice assistants |
| US12327549B2 (en) | 2022-02-09 | 2025-06-10 | Sonos, Inc. | Gatekeeping for voice intent processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105679318A (en) | Display method and device based on voice recognition, display system and air conditioner | |
| CN108509119B (en) | Operation method of electronic device for function execution and electronic device supporting same | |
| US10496382B2 (en) | Machine generation of context-free grammar for intent deduction | |
| CN108121490B (en) | Electronic device, method and server for processing multi-mode input | |
| CN104536978A (en) | Voice data identifying method and device | |
| RU2641468C2 (en) | Method and device of user interface for user terminal | |
| CN108694944B (en) | Methods and devices for generating natural language expressions using frameworks | |
| WO2017152555A1 (en) | Fingerprint identification terminal screen unlocking method and terminal | |
| TW202025138A (en) | Voice interaction method, device and system | |
| CN104123937A (en) | Method, device and system for reminding setting | |
| CN107370649A (en) | Household electric appliance control method, system, control terminal and storage medium | |
| CN107710148A (en) | A kind for the treatment of method and apparatus of Voice command | |
| CN108055405B (en) | Terminal and method for awakening same | |
| CN105783191A (en) | Voice control method, device and system of air conditioner | |
| CN104750378B (en) | The input pattern automatic switching method and device of input method | |
| CN105206275A (en) | Device control method, apparatus and terminal | |
| CN106251863B (en) | A kind of instruction type speech control system and control method based on smart machine | |
| CN106775206B (en) | A screen wake-up method and device for a user terminal, and a user terminal | |
| CN104159294A (en) | A cloud positioning platform based on Bluetooth 4.0 technology | |
| CN203232565U (en) | A multifunctional remote network remote controller | |
| CN109410950B (en) | Voice control method and system of cooking equipment | |
| CN111862965B (en) | Wake-up processing method and device, intelligent sound box and electronic equipment | |
| CN111292744B (en) | Speech instruction recognition method, system and computer readable storage medium | |
| CN105677141A (en) | Application program management method and terminal | |
| CN106302517A (en) | The control method of a kind of industrial equipment, system and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination |