CN107819946A - A kind of method, device and mobile terminal of speech recognition - Google Patents

Abstract

The embodiment of the present invention discloses a voice recognition method, device, and mobile terminal. The method includes: acquiring input fingerprint data; if the fingerprint data is predetermined fingerprint data, acquiring input voice data, and analyzing the voice Voice recognition is performed on the data to obtain a recognition result; when an input operation of the information input box is detected, the recognition result is input into the information input box. Utilizing the embodiment of the present invention, the voice recognition function can be triggered by the fingerprint, and the voice data can be recognized through the voice recognition function, and the corresponding recognition result can be obtained and stored for subsequent use, so that the user can quickly and accurately start the voice recognition function , thereby greatly shortening the calling path of the speech recognition function, and simplifying the processing process of the speech recognition.

Description

Method, device and mobile terminal for speech recognition

technical field

The present invention relates to the field of computer technology, in particular to a voice recognition method, device and mobile terminal.

Background technique

With the continuous development of terminal technology, communication between users through terminals has become an important way for people to communicate. The most commonly used communication is through text and characters. In this process, users need to call the terminal The text and character input method installed in the device, edit the corresponding text or characters and send it to the designated user. However, the speed at which users input text or characters through the input method is generally slow, which easily affects the communication between users.

Voice input has become a way of communication between people due to its advantages of fast speed and high efficiency. However, not all applications support the transmission of voice data between users. Therefore, in order to improve the efficiency of text or character input, The voice data input by the user can be converted into text and characters through speech recognition, and then the converted text and characters can be sent to other users. Moreover, with the advancement of speech recognition algorithms, the speed and accuracy of speech recognition have been further improved, and more and more text and character input methods have added speech recognition functions.

Nevertheless, when the user activates the speech recognition function, he still needs to go through multiple programs or processes to complete it. For example, when the user needs to send a message, he needs to click on the message input box to bring up the text and character input method, and then, from the Find the voice recognition function in the input method, and select voice as input, and text and characters as output, so as to recognize voice data as text or characters and input them into the information input box. It can be seen that the user needs to go through multiple processes to enable the speech recognition function, and the calling path of the speech recognition function is long, which makes the speech recognition processing process cumbersome.

Contents of the invention

An embodiment of the present invention provides a voice recognition method to solve the problem that the processing process of voice recognition in the prior art is relatively cumbersome.

In order to solve the above-mentioned technical problems, the embodiment of the present invention is implemented as follows:

In a first aspect, an embodiment of the present invention provides a method for speech recognition, the method comprising:

Obtain the input fingerprint data;

If the fingerprint data is predetermined fingerprint data, then acquire input voice data, and perform voice recognition on the voice data to obtain a recognition result;

When an input operation of the information input box is detected, the recognition result is input into the information input box.

Optionally, after the recognition result is obtained, the method further includes:

storing the recognition result;

Recording the storage time point of the recognition result;

The step of inputting the recognition result into the information input box when the input operation of the information input box is detected includes:

When an input operation of the information input box is detected and the time interval between the current time point and the storage time point is less than a predetermined first time threshold, the recognition result is input into the information input box.

Optionally, the recognition result includes a plurality of recognition results of voice data,

The inputting the recognition result into the information input box includes:

displaying recognition results of the plurality of speech data;

When receiving an operation instruction to end the selection, acquire a recognition result of at least one voice data selected from the recognition results of the plurality of voice data;

Inputting the acquired recognition result of at least one speech data into the information input box.

Optionally, the inputting the recognition result into the information input box includes:

displaying recognition results of the plurality of speech data;

When receiving an editing instruction, setting the recognition results of the plurality of voice data as a state to be edited;

When an operation instruction to end editing is received, the edited recognition result is obtained;

Input the edited recognition result into the information input box.

Optionally, after displaying the recognition results of the plurality of voice data, the method further includes:

If the time interval between the current time point and the latest stored time point among the recognition results of the plurality of speech data is less than a predetermined second time threshold, input the recognition result of the latest stored time point into the information input box;

When receiving an editing instruction, setting the recognition results of the plurality of voice data to a state to be edited, including:

If the time interval between the current time point and the latest stored time point in the recognition results of the plurality of voice data is not less than the predetermined second time threshold, when an editing instruction is received, the plurality of voice data The recognition result is set to be edited.

Optionally, said acquiring input fingerprint data includes:

When it is detected that the duration of the user's continuous fingerprint recognition reaches a preset duration threshold, the input fingerprint data is acquired.

Optionally, performing speech recognition on the speech data to obtain a recognition result includes:

In the process of performing voice recognition on the voice data, when a predetermined end recognition operation is detected, stop acquiring the voice data and obtain a recognition result; or,

In the process of performing speech recognition on the speech data, when the data volume of the recognition result output per unit time within a predetermined period of time is less than a preset value, stop acquiring the speech data and obtain the recognition result.

In a second aspect, an embodiment of the present invention provides a speech recognition device, the device comprising:

A data acquisition module, configured to acquire input fingerprint data;

A recognition result determining module, used to obtain input voice data if the fingerprint data is predetermined fingerprint data, and perform voice recognition on the voice data to obtain a recognition result;

The first input module is configured to input the recognition result into the information input box when an input operation of the information input box is detected.

Optionally, the device also includes:

a storage module, configured to store the recognition result;

A recording module, configured to record the storage time point of the recognition result;

The first input module is configured to input the recognition result into Enter the information in the box.

Optionally, the recognition result includes a plurality of recognition results of speech data,

The first input module includes:

a display unit for displaying the recognition results of the plurality of speech data;

A selection unit, configured to obtain a recognition result of at least one voice data selected from the recognition results of the plurality of voice data when receiving an operation instruction of selection end;

An input unit, configured to input the acquired recognition result of at least one speech data into the information input box.

Optionally, the first input module includes:

The display unit is used to display the recognition results of the plurality of voice data;

A state setting unit, configured to set the recognition results of the plurality of speech data as a state to be edited when an editing instruction is received;

An editing unit, configured to obtain the edited recognition result when receiving an operation instruction to end editing;

The input unit is configured to input the edited recognition result into the information input box.

Optionally, the device also includes:

The second input module is configured to: if the time interval between the current time point and the latest stored time point among the recognition results of the plurality of speech data is less than a predetermined second time threshold, the latest stored time point The recognition result is input into the information input box;

The state setting unit is configured to: if the time interval between the current time point and the latest stored time point among the recognition results of the plurality of voice data is not less than a predetermined second time threshold, when an editing instruction is received, Setting the recognition results of the plurality of speech data as a state to be edited.

Optionally, the data acquisition module is configured to acquire input fingerprint data when it is detected that the duration of the user's continuous fingerprint identification reaches a preset duration threshold.

Optionally, the recognition result determining module is configured to stop acquiring the voice data and obtain the recognition result when a predetermined end recognition operation is detected during the voice recognition process for the voice data; or, for the voice data During the speech recognition process of the data, when the data volume of the recognition result output per unit time within a predetermined period of time is less than the preset value, the acquisition of the speech data is stopped to obtain the recognition result.

In a third aspect, an embodiment of the present invention provides a mobile terminal, including a processor, a memory, and a computer program stored on the memory and operable on the processor. When the computer program is executed by the processor, The steps of the method for realizing the speech recognition provided by the above-mentioned embodiments

It can be seen from the technical solutions provided by the above embodiments of the present invention that the embodiments of the present invention obtain the input fingerprint data and determine whether the fingerprint data is predetermined fingerprint data, and if so, obtain the input voice data and perform Speech recognition, obtain the recognition result, and then input the recognition result into the information input box when the input operation of the information input box is detected, so that the voice recognition function is triggered by the fingerprint, and the voice data is processed through the voice recognition function Recognition, obtain the corresponding recognition results and store them for subsequent use, so that users can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the processing process of speech recognition.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments described in the present invention. Those skilled in the art can also obtain other drawings based on these drawings without any creative effort.

Fig. 1 is a kind of method embodiment of speech recognition of the present invention;

Fig. 2 is a schematic diagram of a display interface of speech recognition in the present invention;

Fig. 3 is the method embodiment of another kind of speech recognition of the present invention;

Fig. 4 is a schematic diagram of a display interface for selecting a recognition result according to the present invention;

Fig. 5 is another method embodiment of speech recognition of the present invention;

Fig. 6 is another method embodiment of speech recognition of the present invention;

FIG. 7 is an embodiment of a speech recognition device of the present invention;

Fig. 8 is an embodiment of a mobile terminal according to the present invention.

Detailed ways

Embodiments of the present invention provide a voice recognition method, device and mobile terminal.

In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Embodiment one

As shown in FIG. 1 , the embodiment of the present invention provides a method for voice recognition. The execution body of the method may be a terminal device. The terminal device may be a personal computer or other mobile terminal device such as a mobile phone or a tablet computer. The terminal device may be a terminal device used by a user. The method can provide convenience for the user to quickly call the voice recognition function or the voice recognition application. The method specifically may include the following steps:

In step S102, the input fingerprint data is acquired.

Wherein, the fingerprint data may be the data obtained through analysis and processing after the user's fingerprint is collected by the fingerprint identification component, and the fingerprint data may be the fingerprint data of any finger of the user, or the fingerprint data of multiple fingers of the user, etc.

In implementation, with the continuous development of terminal technology, communication between users through terminals has become an important way for people to communicate, and the most commonly used communication is through text and characters. In the process, The user needs to call the text and character input method installed in the terminal device, edit the text or characters through the character buttons provided in the input method, and input the edited text or characters into the text box. After the input is completed, click the text box The send button in the terminal device can send the text and/or characters in the text box to the specified user. However, the speed at which users input text or characters through the input method is generally slow, which easily affects the communication between users. Voice input has become a way of communication between people due to its advantages of fast speed and high efficiency. However, not all applications support the transmission of voice data between users. Therefore, in order to improve the efficiency of text or character input , the embodiment of the present invention provides an implementation manner, that is, the voice data input by the user is converted into text and characters through speech recognition, and then the converted text and characters are sent to other users. With the advancement of speech recognition algorithms, the speed and accuracy of speech recognition have been further improved, and more and more text and character input methods have added speech recognition functions. However, when users start the speech recognition function, they still need to It can be completed through multiple programs or processes. For example, when the user needs to send information, he can click on the information input box. At this time, the terminal device calls out the text and character input method, and finds the voice recognition function from the input method, and then Select the voice recognition function to take effect. At this time, the terminal device turns on the microphone to receive voice data, and recognizes the voice data as text or characters, and inputs them into the information input box. In this way, when the user needs to use the voice recognition function, it needs to go through multiple processes to enable it, which makes the activation of the voice recognition function more complicated (that is, the calling path of the voice recognition function is longer). A technical solution for speech recognition, which may specifically include the following:

Considering that fingerprint recognition is safe, fast, and efficient, fingerprints can be used to activate the voice recognition function. Specifically, the terminal device can be set with a fingerprint setting option. When the user needs to set the fingerprint to activate the voice recognition function, click the fingerprint Setting options, the terminal device obtains and displays the fingerprint setting page, the user can select or set the starting policy of the voice recognition function on the fingerprint setting page, for example, start the voice recognition function through a fingerprint data or a combination of multiple fingerprint data, etc., and then , the user can place one or more fingers of the user on the fingerprint identification component of the terminal device, and obtain one or more fingerprint data of the user through the fingerprint identification component as the fingerprint data for activating the voice recognition function. After the setting is completed, you can click the Finish button on the fingerprint setting page, and the terminal device can obtain the fingerprint data entered by the user on the fingerprint setting page and store the fingerprint data.

When the user needs to start the voice recognition function (for example, when the user needs to record the content of the voice call during the voice call with a friend through the mobile phone, or when the user needs to record the content of the teacher in a lecture or course, or, When it is inconvenient for the user to input characters through the input method to send information to friends, etc.), the user can place the corresponding finger on the fingerprint identification component according to the preset startup strategy, and the fingerprint identification component can collect the fingerprint data of the finger to obtain to the input fingerprint data.

In step S104, if the above-mentioned fingerprint data is predetermined fingerprint data, the input voice data is obtained, and voice recognition is performed on the voice data to obtain a recognition result.

Wherein, the predetermined fingerprint data may be the fingerprint data used to start the voice recognition function, the predetermined fingerprint data may be the fingerprint data of one finger, or the fingerprint data of multiple fingers, and the setting method of the predetermined fingerprint data may refer to the above step S102. related content. The voice data may be voice data of any content input by the user. The recognition result may be text and/or other characters corresponding to the voice data content, for example, the recognition result is composed of text and English letters, or the recognition result is composed of text and numbers.

In practice, after the terminal device obtains the input fingerprint data through the above step S102, it can respectively compare the fingerprint data with the pre-stored fingerprint data in the terminal device, if the fingerprint data is different from the pre-stored fingerprint data, Then, a prompt message may be output to remind the user that the fingerprint data input this time is incorrect, and at this time, the user may re-input the fingerprint data. If the fingerprint data is the same as the predetermined fingerprint data used to start the speech recognition function in the pre-stored fingerprint data, the speech recognition function can be started. At this time, the terminal device can turn on the microphone to collect speech data, and can analyze the collected speech Data, real-time speech recognition is performed according to the speech recognition algorithm preset in the speech recognition function, that is, the collected speech data is converted into text and/or other characters, and the recognition result can be constructed from the converted text and/or other characters, so as to obtain The recognition result of the speech data.

In addition, in the process of real-time recognition of the received voice data, the terminal device can also display the recognition result in real time for the user to preview. The speech recognition function of the terminal device is realized, and the recognition result of the speech data is obtained, which is displayed at a predetermined position on the display interface of the terminal device.

It should be noted that after the terminal device obtains the recognition result, it can store the recognition result in order to be able to use the recognition result later, and its storage location can be preset by the user. Correspondingly, the terminal device is provided with a storage location of the recognition result When the user needs to set the storage location, the setting page can be opened, and the storage area or storage location of the recognition result can be entered in the setting page. After the terminal device obtains the recognition result of the voice data through the processing of the above step S104, the recognition result may be stored in the above storage area or at the storage location.

In addition, in order to increase the speed of data interaction, the recognition results can be stored in the memory or in the cache, so that the retrieval of subsequent recognition results can be improved. In addition, the recognition result can also be stored in the clipboard, so that the retrieval of subsequent recognition results can also be improved.

In step S106, when an input operation of the information input box is detected, the above recognition result is input into the information input box.

In implementation, when a user needs to send information to other users, for example, the user needs to send information to a friend in an instant messaging application, at this time, the user can open the information editing page or chat interface through the terminal device, and the information editing page Alternatively, the chat interface may include an information input box, and the user may click on the information input box, and at this time, the terminal device may detect the input operation of the information input box. Then, the terminal device can obtain the recognition result obtained in the above step S104, and can input the recognition result into the information input box. At this time, the user can further edit the identification result in the information input box. After editing, the user can click the confirm or send button on the information editing page or chat interface, and the terminal device can store or send the identification result in the information input box. result.

The embodiment of the present invention provides a method of speech recognition, by obtaining the input fingerprint data, and judging whether the fingerprint data is predetermined fingerprint data, if yes, obtaining the input speech data, and performing speech recognition on the speech data to obtain The recognition result, and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function, and the corresponding The recognition results are stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the speech recognition processing process.

Embodiment two

As shown in FIG. 3 , the embodiment of the present invention provides a method for voice recognition. The execution subject of the method may be a terminal device, and the terminal device may be a personal computer or other mobile terminal device such as a mobile phone or a tablet computer. The terminal device may be a terminal device used by a user. The method can provide convenience for the user to quickly call the voice recognition function or the voice recognition application. The method specifically may include the following steps:

In step S302, when it is detected that the duration of the user's continuous fingerprint identification reaches a preset duration threshold, the input fingerprint data is acquired.

Wherein, the preset duration threshold can be set according to actual conditions, such as 2 seconds or 3 seconds, etc. specifically.

In the implementation, it is considered that there may be various settings in the terminal device for authentication through fingerprints or for launching applications, for example, unlocking the screen of the mobile phone through fingerprints or performing payment verification through fingerprints. In order to distinguish the above fingerprint settings, a combination of fingerprints and specific operations can be used to reduce interference with other application programs. In the embodiment of the present invention, the fingerprint and the duration of continuous fingerprint recognition can be used to trigger the start of the voice recognition function. Specifically, the user can input the fingerprint on the fingerprint setting page and set the preset duration threshold for continuous fingerprint recognition, for example, The user can input the fingerprint data of the index finger into the fingerprint setting page through the fingerprint identification component, and set the duration as 2 seconds at the preset duration threshold. When the user needs to start the voice recognition function, the user can place the index finger on the fingerprint recognition component. At this time, the terminal device can detect the duration of the user’s continuous fingerprint recognition through the fingerprint recognition component. If the user keeps the index finger on the fingerprint recognition component to reach In 2 seconds, the terminal device can determine that the user needs to activate the voice recognition function. At this time, the fingerprint recognition component can collect the fingerprint data of the finger, so as to obtain the input fingerprint data.

It should be noted that, the above method of combining fingerprints with specific operations can not only reduce interference with operations of other application programs, but also avoid user misoperations.

In step S304, if the above-mentioned fingerprint data is predetermined fingerprint data, the input voice data is obtained, and during the voice recognition process of the voice data, when the data volume of the recognition result output per unit time within the predetermined time length is less than the preset value , stop acquiring voice data and get the recognition result.

Wherein, the preset value can be set according to the actual situation, for example, 1 word or character, or 2 words or characters. The data volume of the recognition result output per unit time may specifically be the number of characters or characters recognized per second, or the number of characters or characters recognized every 3 seconds.

In implementation, if the above-mentioned fingerprint data is predetermined fingerprint data, the specific processing process of obtaining the input voice data and performing voice recognition on the voice data can refer to the relevant content of step S104 in the first embodiment above, and will not repeat them here. . In order to improve the efficiency of speech recognition, a processing mechanism for detecting the end of speech recognition can be set, that is, a threshold (that is, a preset value) of the data volume of the recognition result output per unit time within a predetermined period of time can be set, specifically, within 3 consecutive seconds Within, the preset value of valid recognition results output per second is 1 word or character. In the process of voice recognition of the voice data, the terminal device can detect the speed of the output recognition results in real time. When it is detected that within 3 consecutive seconds, the data volume of valid recognition results output per second is less than 1 character or characters, it can be determined that the user has stopped inputting voice data. At this time, the terminal device can stop voice recognition and turn off the voice recognition function, so as to obtain the final recognition result.

In addition to stopping the speech recognition process through automatic recognition, it can also be realized through manual stop by the user, which may specifically include the following content: in the process of speech recognition of the above-mentioned speech data, when a predetermined end recognition operation is detected, Stop acquiring voice data and get the recognition result.

Among them, the end of the recognition operation can be realized in various ways, for example, it can be realized by inputting preset fingerprint data, or it can be realized by combining the fingerprint with a specific operation (such as the duration of the above-mentioned user’s continuous fingerprint recognition, etc.), Alternatively, it may be implemented by clicking a specified button, which is not limited in this embodiment of the present invention.

In the implementation, take the combination of fingerprint and specific operation as an example, when the user needs to stop the voice recognition during the speech recognition process of the above speech data, the finger corresponding to the preset fingerprint data can be placed on the fingerprint The recognition component remains on for a certain period of time. At this time, the terminal device can determine that the user needs to stop the speech recognition, and then the speech recognition function can be turned off, so as to obtain the final recognition result.

It should be noted that, if the voice recognition function is activated through the processing methods of the above steps S302 and S304 due to the user's misoperation, the terminal device can display the recognition result on the screen for the user to preview, so that the user knows the voice recognition function. is turned on to direct users to turn off speech recognition in a timely manner.

In step S306, the above recognition result is stored.

For the specific processing procedure of the above step S306, reference may be made to the relevant content in the above step S104, and details are not repeated here.

Considering that there may be multiple input voice data, correspondingly, the recognition result should also include the recognition results of multiple voice data, and the recognition result selected by the user may be one or more of them. For this reason, this The embodiment of the invention also provides a corresponding processing procedure, for details, refer to the following steps S308 to S316.

In step S308, the storage time point of the recognition result is recorded.

In step S310, when an input operation of the information input box is detected and the time interval between the current time point and the above-mentioned storage time point is less than a predetermined first time threshold, a plurality of voice data recognition results are displayed.

Wherein, the first time threshold may be set according to actual conditions, specifically, for example, 20 seconds or 30 seconds.

In implementation, in order to facilitate data storage, the identification result in step S306 above may be stored in the clipboard. When the user needs to send information to other users, for example, the user needs to send information to friends in an instant messaging application, at this time, the user can open the information editing page or chat interface through the terminal device, and the information editing page or chat interface An information input box may be included, and the user may click on the information input box, and at this time, the terminal device may detect the input operation of the information input box. In order to increase the speed of information transmission, the terminal device can first judge whether the above recognition result needs to be used as input information, and its judgment strategy can be set based on the time interval between the current time point and the above storage time point, that is, setting the current time point The first time threshold of the time interval between the above-mentioned storage time point, after the terminal device detects the input operation of the information input box, it can obtain the current time point and compare the current time point with the above-mentioned storage time point, if the current If the time interval between the time point and the above-mentioned storage time point is not less than the predetermined first time threshold, the terminal device invokes the input method. At this time, the user can input characters, numbers or letters through the input method. If the time interval between the current time point and the above-mentioned storage time point is less than the predetermined first time threshold, the terminal device may determine that the user needs to use the above-mentioned recognition result as input information. At this time, as shown in FIG. 4, the terminal device may Open the clipboard to display the recognition results of multiple voice data (specifically, the recognition results can be displayed in the form of a drop-down list, or the recognition results can be displayed in a pop-up new page, etc.), for the user to view and select.

It should be noted that, considering that the recognition results include multiple different recognition results, and the storage time points of multiple different recognition results may be different, therefore, when calculating the time interval between the current time point and the above-mentioned storage time point , can be achieved by the following way, the time interval between the current time point and the most recent storage time point among the above storage time points, or calculating the average value of the above storage time points, and then calculating the time interval between the current time point and the average value time interval etc.

In step S312, when the operation instruction of selecting and ending is received, at least one recognition result of voice data selected from a plurality of recognition results of voice data is acquired.

Among them, the operation instruction of selection end can be realized in various ways, for example, triggering the operation instruction of selection end by clicking a specified button, or triggering the operation instruction of selection end by any other preset operation, etc., which is not limited in the embodiment of the present invention. .

In implementation, as shown in Figure 4, after the terminal device displays a plurality of recognition results of voice data, the user can find the recognition result to be used and select the corresponding recognition result (as shown in Figure 4, the user selects the recognition result 1) After the selection is completed, you can click the OK button set on the page displaying the recognition result. At this time, the terminal device can generate an operation instruction to end the selection, and obtain the recognition result of at least one voice data selected by the user from the page displaying the recognition result. .

In step S314, the acquired recognition result of at least one speech data is input into the above-mentioned information input box.

It should be noted that the processing of the above steps S310 to S314 is to input the corresponding recognition results into the information input box by the way selected by the user. In practical applications, in order to simplify the processing flow, the information input can also be completed in the following way The processing of inputting the corresponding recognition result in the box may specifically include the following content: when the input operation of the information input box is detected, and the time interval between the current time point and the above-mentioned storage time point is less than the predetermined first time threshold, the The above identification results are input into the information input box.

In addition, considering that the recognition results include multiple different recognition results, and the overall data volume of multiple different recognition results may be large, when inputting the corresponding recognition results into the information input box, the latest stored The recognition result of the time point is input into the information input box.

In step S316, the recognition result in the information input box is stored or transmitted.

The embodiment of the present invention provides a method of speech recognition, by obtaining the input fingerprint data, and judging whether the fingerprint data is predetermined fingerprint data, if yes, obtaining the input speech data, and performing speech recognition on the speech data to obtain The recognition result, and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function, and the corresponding The recognition results are stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the speech recognition processing process.

In addition, the embodiment of the present invention optimizes the triggering speed, parallelism and closing intelligence of the speech recognition function, realizes the rapid calling of the recognition results, improves the possibility of further editing and multiplexing of multiple recognition results, and effectively expands the text Or character input methods and usage scenarios and efficiency of speech recognition.

Embodiment Three

As shown in FIG. 5, the embodiment of the present invention provides a method for voice recognition. The execution subject of the method may be a terminal device. The terminal device may be a personal computer or other mobile terminal device such as a mobile phone or a tablet computer. The terminal device may be a terminal device used by a user. The method can provide convenience for the user to quickly call the speech recognition function or the speech recognition application. The method specifically may include the following steps:

In step S502, when it is detected that the duration of the user's continuous fingerprint identification reaches a preset duration threshold, the input fingerprint data is acquired.

In step S504, if the above-mentioned fingerprint data is predetermined fingerprint data, the input voice data is acquired, and during the voice recognition process of the voice data, when the data volume of the recognition result output per unit time within the predetermined duration is less than the preset value , stop acquiring voice data and get the recognition result.

In addition to stopping the speech recognition process through automatic recognition, it can also be realized through manual stop by the user, which may specifically include the following content: in the process of speech recognition of the above-mentioned speech data, when a predetermined end recognition operation is detected, Stop acquiring voice data and get the recognition result.

In step S506, the above recognition result is stored.

The step content of the above step S502～step S506 is the same as the step content of the step S302～step S306 in the above embodiment 2 respectively, the specific processing process of the step S502～step S506 can refer to the relevant content of the above step S302～step S306 respectively, in This will not be repeated here.

Considering that there may be multiple input voice data, correspondingly, the recognition result should also include the recognition results of multiple voice data, and the recognition result selected by the user may be one or more of the recognition results, and the user may It is also necessary to perform editing operations such as deleting, sorting, or modifying the selected recognition results. For this reason, the embodiment of the present invention also provides a corresponding processing procedure. For details, please refer to the following steps S508 to S518.

In step S508, the storage time point of the recognition result is recorded.

In step S510, when the input operation of the information input box is detected, and the time interval between the current time point and the above-mentioned storage time point is less than a predetermined first time threshold, a plurality of voice data recognition results are displayed.

The step content of the above step S508～step S510 is the same as the step content of the step S308～step S310 in the above embodiment 2 respectively, the specific processing process of the step S508～step S510 can refer to the relevant content of the above step S308～step S310 respectively, in This will not be repeated here.

In step S512, when an editing instruction is received, the above-mentioned recognition results of the plurality of speech data are set as a state to be edited.

In implementation, a plurality of operation buttons may be included in the page displaying the recognition results of a plurality of voice data, for example, an edit button is added in Fig. button, confirm button, etc., wherein the edit button can guide the user to edit the recognition result. If the user sees that the displayed recognition result cannot completely match the information that the user wants to write, he can click the edit button. At this time, the terminal device can set the recognition results of multiple voice data to the edit page. Correspondingly, multiple The recognition results of voice data are set to the pending editing state.

In step S514, when an operation instruction to end editing is received, the edited recognition result is acquired.

Wherein, the operation instruction to end editing can be realized in various ways, for example, triggering the operation instruction to end editing by clicking a specified button, or triggering the operation instruction to end editing through any other preset operation, etc., which is not limited in this embodiment of the present invention .

In the implementation, the user can perform any one or more operations of deleting, modifying, and sorting the recognition results of multiple voice data on the editing page, and finally can edit the recognition results of multiple voice data into the After editing the information, you can click the OK button on the edit page. At this time, the terminal device can generate an operation instruction to end editing and execute the operation instruction to end editing, so as to obtain the recognition result of the user's editing completion on the edit page (that is, edit After the recognition results).

In step S516, input the above-mentioned edited recognition result into the information input box.

In step S518, the recognition result in the information input box is stored or sent.

The embodiment of the present invention provides a method of speech recognition, by obtaining the input fingerprint data, and judging whether the fingerprint data is predetermined fingerprint data, if yes, obtaining the input speech data, and performing speech recognition on the speech data to obtain The recognition result, and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function, and the corresponding The recognition results are stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the speech recognition processing process.

In addition, the embodiment of the present invention optimizes the triggering speed, parallelism and closing intelligence of the speech recognition function, realizes the rapid calling of the recognition results, improves the possibility of further editing and multiplexing of multiple recognition results, and effectively expands the text Or character input methods and usage scenarios and efficiency of speech recognition.

Embodiment four

As shown in FIG. 6, the embodiment of the present invention provides a method for voice recognition. The execution body of the method may be a terminal device, and the terminal device may be a personal computer or other mobile terminal device such as a mobile phone or a tablet computer. The terminal device may be a terminal device used by a user. The method can provide convenience for the user to quickly call the voice recognition function or the voice recognition application. The method specifically may include the following steps:

In step S602, when it is detected that the duration of the user's continuous fingerprint identification reaches a preset duration threshold, the input fingerprint data is acquired.

In step S604, if the above-mentioned fingerprint data is predetermined fingerprint data, the input voice data is acquired, and during the voice recognition process of the voice data, when the data volume of the recognition result output per unit time within the predetermined duration is less than the preset value , stop acquiring voice data and get the recognition result.

In addition to stopping the speech recognition process through automatic recognition, it can also be realized through manual stop by the user, which may specifically include the following content: in the process of speech recognition of the above-mentioned speech data, when a predetermined end recognition operation is detected, Stop acquiring voice data and get the recognition result.

In step S606, the above recognition result is stored.

The step content of the above step S602～step S606 is the same as the step content of the step S302～step S306 in the above embodiment 2 respectively, the specific processing process of the step S602～step S606 can refer to the relevant content of the above step S302～step S306 respectively, in This will not be repeated here.

Considering that there may be multiple input voice data, correspondingly, the recognition result should also include the recognition results of multiple voice data, and the recognition result selected by the user may be one or more of the recognition results, and the user may It is most desirable to use the recognition results at the most recent storage point in time, or the user may also need to perform edit operations such as deleting, sorting, or modifying the recognition results. For this reason, the embodiment of the present invention also provides a corresponding processing process. For details, please refer to the following Step S608 to step S620.

In step S608, the storage time point of the recognition result is recorded.

In step S610, when the input operation of the information input box is detected, and the time interval between the current time point and the above-mentioned storage time point is less than a predetermined first time threshold, the recognition results of multiple voice data are displayed.

The step content of the above step S608 ~ step S610 is the same as the step content of the step S308 ~ step S310 in the above embodiment 2 respectively. This will not be repeated here.

Considering that if the user has just completed the speech recognition process and then performs the information input operation, at this time, the user may most want to use the recognition result at the most recent storage point in time, therefore, a corresponding strategy can be set so that the recognition result can be edited before editing the recognition result. It is judged whether the user wants to use the recognition result at the latest storage time point, if not, the processing of the following steps S612 to S616 may be performed, and if yes, the processing of the following step S618 may be performed.

In step S612, if the time interval between the current time point and the latest stored time point in the recognition results of the above-mentioned multiple voice data is not less than the predetermined second time threshold, when an editing instruction is received, the multiple voice data The recognition result of the data is set to be edited.

Wherein, the second time threshold may be set according to actual conditions, such as 10 seconds or 8 seconds, etc. specifically. Moreover, the first time threshold is greater than the second time threshold, specifically, the first time threshold is 20 seconds, the second time threshold is 10 seconds, and so on.

In step S614, when an operation instruction to end editing is received, the edited recognition result is acquired.

In step S616, input the above-mentioned edited recognition result into the information input box.

The step content of the above step S612～step S616 is the same as the step content of the step S512～step S516 in the third embodiment respectively, the specific processing process of the step S612～step S616 can refer to the relevant content of the above step S512～step S516 respectively, in This will not be repeated here.

In step S618, if the time interval between the current time point and the latest stored time point among the recognition results of the plurality of voice data is less than the predetermined second time threshold, then input the recognition result of the latest stored time point into the information input box.

In implementation, for example, the recognition results of a plurality of speech data include three recognition results of speech data, which are respectively recognition result 1, recognition result 2 and recognition result 3, wherein the storage time point of recognition result 1 is 10:32 :20, the storage time point of recognition result 2 is 10:31:50, the storage time point of recognition result 3 is 10:31:10, the first time threshold is 20 seconds, the second time threshold is 10 seconds, the current If the time point is 10:32:28, it can be determined that the latest storage time point is 10:32:20, and the time interval between the current time point 10:32:28 and the latest storage time point 10:32:20 is 8 seconds The clock is less than the predetermined second time threshold of 10 seconds, therefore, the recognition result 1 whose storage time point is 10:32:20 can be directly input into the information input box.

It should be noted that the user can still edit the recognition result input into the information input box.

In step S620, the recognition result in the information input box is stored or transmitted.

In addition, if the recognition result in the clipboard includes information such as mobile phone number, email address, link, account number, etc., the user can perform a series of shortcut operations such as speed dialing, sending a short message, and opening a browser.

The embodiment of the present invention provides a method of speech recognition, by obtaining the input fingerprint data, and judging whether the fingerprint data is predetermined fingerprint data, if yes, obtaining the input speech data, and performing speech recognition on the speech data to obtain The recognition result, and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function, and the corresponding The recognition results are stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the speech recognition processing process.

In addition, the embodiment of the present invention optimizes the triggering speed, parallelism and closing intelligence of the speech recognition function, realizes the rapid calling of the recognition results, improves the possibility of further editing and multiplexing of multiple recognition results, and effectively expands the text Or character input methods and usage scenarios and efficiency of speech recognition.

Embodiment five

The above is the speech recognition method provided by the embodiment of the present invention. Based on the same idea, the embodiment of the present invention also provides a speech recognition device, as shown in FIG. 7 .

The device for speech recognition includes: a data acquisition module 701, a recognition result determination module 702 and a first input module 703, wherein:

A data acquisition module 701, configured to acquire input fingerprint data;

A recognition result determining module 702, configured to obtain input voice data if the fingerprint data is predetermined fingerprint data, and perform voice recognition on the voice data to obtain a recognition result;

The first input module 703 is configured to input the recognition result into the information input box when an input operation of the information input box is detected.

In an embodiment of the present invention, the device further includes:

a storage module, configured to store the recognition result;

A recording module, configured to record the storage time point of the recognition result;

The first input module 703 is configured to input the recognition result when an input operation of the information input box is detected and the time interval between the current time point and the storage time point is less than a predetermined first time threshold into the information input box.

In the embodiment of the present invention, the recognition result includes a plurality of recognition results of voice data,

The first input module 703 includes:

a display unit for displaying the recognition results of the plurality of speech data;

A selection unit, configured to obtain a recognition result of at least one voice data selected from the recognition results of the plurality of voice data when receiving an operation instruction of selection end;

An input unit, configured to input the acquired recognition result of at least one speech data into the information input box.

In the embodiment of the present invention, the first input module 703 includes:

The display unit is used to display the recognition results of the plurality of voice data;

A state setting unit, configured to set the recognition results of the plurality of speech data as a state to be edited when an editing instruction is received;

An editing unit, configured to obtain the edited recognition result when receiving an operation instruction to end editing;

The input unit is configured to input the edited recognition result into the information input box.

In an embodiment of the present invention, the device further includes:

The second input module is configured to: if the time interval between the current time point and the latest stored time point among the recognition results of the plurality of speech data is less than a predetermined second time threshold, the latest stored time point The recognition result is input into the information input box;

The state setting unit is configured to: if the time interval between the current time point and the latest stored time point among the recognition results of the plurality of voice data is not less than a predetermined second time threshold, when an editing instruction is received, Setting the recognition results of the plurality of speech data as a state to be edited.

In an embodiment of the present invention, the device further includes:

A processing module, configured to store or send the recognition result in the information input box.

In the embodiment of the present invention, the data acquisition module 701 is configured to acquire input fingerprint data when it is detected that the duration of the user's continuous fingerprint identification reaches a preset duration threshold.

In the embodiment of the present invention, the recognition result determining module 702 is configured to stop acquiring the voice data and obtain the recognition result when a predetermined end recognition operation is detected during the speech recognition process of the speech data; or, During the voice recognition process of the voice data, when the data volume of the recognition result output per unit time within a predetermined period of time is less than a preset value, the acquisition of the voice data is stopped to obtain the recognition result.

The speech recognition apparatus provided by the embodiment of the present invention can implement various processes implemented by the terminal device in the method embodiments in FIG. 1 to FIG. 6 , and details are not repeated here to avoid repetition.

An embodiment of the present invention provides a device for voice recognition, by acquiring input fingerprint data, and judging whether the fingerprint data is predetermined fingerprint data, if yes, acquiring input voice data, and performing voice recognition on the voice data to obtain The recognition result, and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function, and the corresponding The recognition results are stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the speech recognition processing process.

In addition, the embodiment of the present invention optimizes the triggering speed, parallelism and closing intelligence of the speech recognition function, realizes the rapid calling of the recognition results, improves the possibility of further editing and multiplexing of multiple recognition results, and effectively expands the text Or character input methods and usage scenarios and efficiency of speech recognition.

Embodiment six

FIG. 8 is a schematic diagram of a hardware structure of a mobile terminal implementing various embodiments of the present invention.

The mobile terminal 800 includes, but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, a processor 810, and Power supply 811 and other components. Those skilled in the art can understand that the structure of the mobile terminal shown in Figure 8 does not constitute a limitation on the mobile terminal, and the mobile terminal may include more or less components than shown in the figure, or combine some components, or different components layout. In the embodiment of the present invention, the mobile terminal includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palmtop computer, a vehicle-mounted terminal, a wearable device, and a pedometer.

Wherein, the processor 810 is configured to obtain input fingerprint data;

The processor 810 is further configured to acquire input voice data if the fingerprint data is predetermined fingerprint data, and perform voice recognition on the voice data to obtain a recognition result;

The input unit 804 is configured to input the recognition result into the information input box when an input operation of the information input box is detected.

In addition, a memory 809 is configured to store the recognition result;

The processor 810 is further configured to record the storage time point of the recognition result;

The input unit 804 is further configured to input the recognition result into the information input box.

In addition, the recognition result includes a plurality of recognition results of voice data,

The input unit 804 is configured to display the recognition results of the plurality of voice data; when receiving an operation instruction to end the selection, acquire a recognition result of at least one voice data selected from the recognition results of the multiple voice data; The acquired recognition result of at least one speech data is input into the information input box.

In addition, the input unit 804 is configured to display the recognition results of the plurality of voice data; when an editing instruction is received, set the recognition results of the plurality of voice data to a state to be edited; when receiving an operation instruction to end editing , acquire the edited recognition result; and input the edited recognition result into the information input box.

In addition, the input unit 804 is further configured to: if the time interval between the current time point and the latest storage time point in the recognition results of the plurality of speech data is less than a predetermined second time threshold, then set the latest storage time The recognition result of the point is input into the information input box;

The input unit 804 is further configured to: if the time interval between the current time point and the latest stored time point among the recognition results of the plurality of speech data is not less than a predetermined second time threshold, when an editing instruction is received, the The recognition results of the plurality of voice data are set to be edited.

In addition, the processor 810 is further configured to store or send the recognition result in the information input box.

In addition, the processor 810 is further configured to obtain input fingerprint data when it is detected that the duration of the user's continuous fingerprint identification reaches a preset duration threshold.

In addition, the processor 810 is also used for performing speech recognition on the speech data. When a predetermined end recognition operation is detected, the acquisition of speech data is stopped to obtain a recognition result; or, speech recognition is performed on the speech data. During the process, when the data volume of the recognition result output per unit time within a predetermined period of time is less than the preset value, the acquisition of voice data is stopped and the recognition result is obtained.

An embodiment of the present invention provides a mobile terminal, by acquiring input fingerprint data, and judging whether the fingerprint data is predetermined fingerprint data, and if so, acquiring input voice data, performing voice recognition on the voice data, and obtaining a recognition result , and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function to obtain the corresponding recognition The result is stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the processing process of the speech recognition.

In addition, the embodiment of the present invention optimizes the triggering speed, parallelism and closing intelligence of the speech recognition function, realizes the rapid calling of the recognition results, improves the possibility of further editing and multiplexing of multiple recognition results, and effectively expands the text Or character input methods and usage scenarios and efficiency of speech recognition.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 801 can be used for receiving and sending signals during sending and receiving information or during a call. Specifically, after receiving the downlink data from the base station, the processor 810 processes it; Uplink data is sent to the base station. Generally, the radio frequency unit 801 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 801 can also communicate with the network and other devices through a wireless communication system.

The mobile terminal provides users with wireless broadband Internet access through the network module 802, such as helping users send and receive emails, browse web pages, and access streaming media.

The audio output unit 803 may convert audio data received by the radio frequency unit 801 or the network module 802 or stored in the memory 809 into an audio signal and output as sound. Also, the audio output unit 803 can also provide audio output related to a specific function performed by the mobile terminal 800 (for example, call signal reception sound, message reception sound, etc.). The audio output unit 803 includes a speaker, a buzzer, a receiver, and the like.

The input unit 804 is used for receiving audio or video signals. The input unit 804 may include a graphics processing unit (Graphics Processing Unit, GPU) 8041 and a microphone 8042, and the graphics processing unit 8041 is used for still pictures or video images obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The data is processed. The processed image frames may be displayed on the display unit 806 . The image frames processed by the graphics processor 8041 may be stored in the memory 809 (or other storage media) or sent via the radio frequency unit 801 or the network module 802 . The microphone 8042 can receive sound, and can process such sound into audio data. The processed audio data can be converted into a format that can be sent to a mobile communication base station via the radio frequency unit 801 for output in the case of a phone call mode.

The mobile terminal 800 also includes at least one sensor 805, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 8061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 8061 and the / or backlighting. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is still, and can be used to identify the posture of mobile terminals (such as horizontal and vertical screen switching, related games, etc.) , magnetometer posture calibration), vibration recognition-related functions (such as pedometer, knocking), etc.; the sensor 805 can also include fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, Infrared sensors, etc., will not be repeated here.

The display unit 806 is used to display information input by the user or information provided to the user. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.

The user input unit 807 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the mobile terminal. Specifically, the user input unit 807 includes a touch panel 8071 and other input devices 8072 . The touch panel 8071, also referred to as a touch screen, can collect touch operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger or a stylus on the touch panel 8071 or near the touch panel 8071). operate). The touch panel 8071 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to For the processor 810, receive the command sent by the processor 810 and execute it. In addition, the touch panel 8071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 8071 , the user input unit 807 may also include other input devices 8072 . Specifically, other input devices 8072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.

Furthermore, the touch panel 8071 can be covered on the display panel 8061, and when the touch panel 8071 detects a touch operation on or near it, it will be sent to the processor 810 to determine the type of the touch event, and then the processor 810 will The type of event provides a corresponding visual output on the display panel 8061. Although in FIG. 8, the touch panel 8071 and the display panel 8061 are used as two independent components to realize the input and output functions of the mobile terminal, in some embodiments, the touch panel 8071 and the display panel 8061 can be integrated. The implementation of the input and output functions of the mobile terminal is not specifically limited here.

The interface unit 808 is an interface for connecting an external device to the mobile terminal 800 . For example, an external device may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, audio input/output (I/O) ports, video I/O ports, headphone ports, and more. The interface unit 808 can be used to receive input from an external device (for example, data information, power, etc.) transfer data between devices.

The memory 809 can be used to store software programs as well as various data. The memory 809 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created by the use of mobile phones (such as audio data, phonebook, etc.), etc. In addition, the memory 809 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

The processor 810 is the control center of the mobile terminal, which uses various interfaces and lines to connect various parts of the entire mobile terminal, by running or executing software programs and/or modules stored in the memory 809, and calling data stored in the memory 809 , execute various functions of the mobile terminal and process data, so as to monitor the mobile terminal as a whole. The processor 810 may include one or more processing units; preferably, the processor 810 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem The processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 810 .

The mobile terminal 800 can also include a power supply 811 (such as a battery) for supplying power to various components. Preferably, the power supply 811 can be logically connected to the processor 810 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. and other functions.

Preferably, the embodiment of the present invention also provides a mobile terminal, including a processor 810, a memory 809, and a computer program stored in the memory 809 and operable on the processor 810. When the computer program is executed by the processor 810 The various processes of the above speech recognition method embodiment can achieve the same technical effect, so in order to avoid repetition, details will not be repeated here.

Embodiment seven

The embodiment of the present invention also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the above-mentioned voice recognition method embodiment is realized, and the same Technical effects, in order to avoid repetition, will not be repeated here. Wherein, the computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), a magnetic disk or an optical disk, and the like.

An embodiment of the present invention provides a computer-readable storage medium. By acquiring input fingerprint data and determining whether the fingerprint data is predetermined fingerprint data, if yes, acquiring input voice data and performing voice recognition on the voice data, The recognition result is obtained, and then when the input operation of the information input box is detected, the recognition result is input into the information input box, so that the voice recognition function is triggered by the fingerprint, and the voice data is recognized through the voice recognition function, and the obtained The corresponding recognition results are stored for subsequent use, so that the user can quickly and accurately start the speech recognition function, thereby greatly shortening the calling path of the speech recognition function and simplifying the processing process of the speech recognition.

In addition, the embodiment of the present invention optimizes the triggering speed, parallelism and closing intelligence of the speech recognition function, realizes the rapid calling of the recognition results, improves the possibility of further editing and multiplexing of multiple recognition results, and effectively expands the text Or character input methods and usage scenarios and efficiency of speech recognition.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and/or nonvolatile memory such as read only memory (ROM) or flash RAM. Memory is an example of computer readable media.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The above descriptions are only examples of the present invention, and are not intended to limit the present invention. Various modifications and variations of the present invention will occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims (15)

1. A method of speech recognition, the method comprising:

acquiring input fingerprint data;

if the fingerprint data is preset fingerprint data, acquiring input voice data, and performing voice recognition on the voice data to obtain a recognition result;

and when an input operation instruction of an information input box is detected, inputting the identification result into the information input box.

2. The method of claim 1, wherein after obtaining the recognition result, the method further comprises:

storing the recognition result;

recording the storage time point of the identification result;

when an input operation instruction of an information input box is detected, inputting the recognition result into the information input box, wherein the method comprises the following steps:

when the input operation of an information input box is detected, and the time interval between the current time point and the storage time point is smaller than a preset first time threshold value, inputting the identification result into the information input box.

3. The method according to claim 2, wherein the recognition result includes a plurality of recognition results of voice data,

the inputting the recognition result into the information input box includes:

displaying recognition results of the plurality of voice data;

when an operation instruction of finishing selection is received, acquiring a recognition result of at least one voice data selected from the recognition results of the plurality of voice data;

and inputting the obtained recognition result of at least one voice datum into the information input box.

4. The method of claim 3, wherein the inputting the recognition result into the information input box comprises:

displaying recognition results of the plurality of voice data;

when an editing instruction is received, setting the recognition results of the voice data into a state to be edited;

when an operation instruction for finishing editing is received, acquiring an edited identification result;

and inputting the edited recognition result into the information input box.

5. The method of claim 4, wherein after displaying the recognition results of the plurality of speech data, the method further comprises:

inputting a recognition result of a most recent storage time point into the information input box if a time interval between a current time point and the most recent storage time point among the recognition results of the plurality of voice data is less than a predetermined second time threshold;

when receiving an editing operation instruction, setting the recognition results of the plurality of voice data to be in a state to be edited, including:

and if the time interval between the current time point and the latest storage time point in the recognition results of the plurality of voice data is not less than a preset second time threshold, setting the recognition results of the plurality of voice data to be in a state to be edited when an editing operation instruction is received.

6. The method of claim 1, wherein the obtaining input fingerprint data comprises:

and when detecting that the time for continuously carrying out fingerprint identification by the user reaches a preset time threshold, acquiring the input fingerprint data.

7. The method of claim 1, wherein performing speech recognition on the speech data to obtain a recognition result comprises:

in the process of carrying out voice recognition on the voice data, when a preset recognition finishing operation is detected, stopping acquiring the voice data to obtain a recognition result; or,

and in the process of carrying out voice recognition on the voice data, stopping acquiring the voice data when the data volume of the recognition result output in unit time within the preset time length is less than a preset numerical value, and obtaining the recognition result.

8. An apparatus for speech recognition, the apparatus comprising:

the data acquisition module is used for acquiring input fingerprint data;

the identification result determining module is used for acquiring input voice data and carrying out voice identification on the voice data to obtain an identification result if the fingerprint data is preset fingerprint data;

the first input module is used for inputting the recognition result into the information input box when an input operation instruction of the information input box is detected.

9. The apparatus of claim 8, further comprising:

the storage module is used for storing the identification result;

the recording module is used for recording the storage time point of the identification result;

the first input module is used for inputting the identification result into the information input box when the input operation instruction of the information input box is detected and the time interval between the current time point and the storage time point is smaller than a preset first time threshold.

10. The apparatus according to claim 9, wherein the recognition result includes a plurality of recognition results of voice data,

the first input module includes:

a display unit for displaying recognition results of the plurality of voice data;

the selection unit is used for acquiring the recognition result of at least one voice data selected from the recognition results of the plurality of voice data when receiving the operation instruction of finishing the selection;

an input unit for inputting a recognition result of the acquired at least one voice data into the information input box.

11. The apparatus of claim 10, wherein the first input module comprises:

the display unit is used for displaying the recognition results of the plurality of voice data;

the state setting unit is used for setting the recognition results of the voice data into a state to be edited when an editing operation instruction is received;

the editing unit is used for acquiring an edited identification result when an operation instruction for finishing editing is received;

and the input unit is used for inputting the edited recognition result into the information input box.

12. The apparatus of claim 11, further comprising:

a second input module for inputting the recognition result of the latest storage time point into the information input box if a time interval between a current time point and the latest storage time point among the recognition results of the plurality of voice data is less than a predetermined second time threshold;

the state setting unit is used for setting the recognition results of the plurality of voice data into a state to be edited when an editing instruction is received if the time interval between the current time point and the latest storage time point in the recognition results of the plurality of voice data is not less than a preset second time threshold.

13. The apparatus of claim 8, wherein the data acquiring module is configured to acquire the input fingerprint data when it is detected that a duration of continuous fingerprint recognition by the user reaches a preset duration threshold.

14. The apparatus according to claim 8, wherein the recognition result determining module is configured to, during the speech recognition of the speech data, stop obtaining the speech data when a predetermined recognition ending operation is detected to obtain a recognition result; or stopping acquiring the voice data to obtain the recognition result when the data volume of the recognition result output in unit time within the preset time length is less than a preset numerical value in the process of carrying out voice recognition on the voice data.

15. A mobile terminal, characterized in that it comprises a processor, a memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the method of speech recognition according to any one of claims 1 to 7.