JP2005309065A - Speech recognition result output device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent a predetermined word recognized by a voice recognition function from being output as it is visible.
Only when a recognized word recognized by speech is registered in association with an output character in a word list (Y in S4), an output character associated with the recognized word from the word list is displayed. Extracted (S5) and output (printed or displayed) so as to be visible (S6). As a result, various recognitions can be made by associating the same output characters with various recognition words in the word list, for example, without directly outputting (printing or displaying) the words recognized by the voice recognition function. Since the text can be output (printed or displayed) in a visible manner as the same text, the text that has been output (printed or displayed) in a visible manner has a sense of unity, looks neat, and is easy to organize / manage can do.
[Selection] Figure 7

Description

  The present invention relates to a speech recognition result output device that is equipped with a speech recognition function and outputs a speech recognition-recognized wording so as to be visible.

  A speech recognition technology (for example, see Patent Document 1) that analyzes speech digital data generated based on input speech and converts human voice into text is used in personal computers and the like. The voice converted into text by this voice recognition technology, that is, the words that have been voice-recognized, are displayed on the screen or printed and utilized.

Japanese Patent Laid-Open No. 2001-56697

  However, there are cases where it is better not to display or print the words recognized by the voice recognition technology as they are.

  For example, in a bento restaurant, you may want to print “Hokkaido salmon lunch”. However, it is assumed that the input phrase varies from person to person, such as “hokkaisake”, “hokkaishake”, and “hokkaido usakeben”. Even when the input words are unified, it is not always possible to correctly speak up to the pronunciation of “salmon” and “salmon”. Also, even if you can speak correctly by practicing, if you are in a busy situation, you may omit words or return words. In such a case, there is no sense of unity in the words displayed on the screen or printed, the appearance is cluttered, and it becomes difficult to organize / manage.

  Also, if the customer's name is abandoned or becomes “Saito-chan” in the reservation memo of the lunch box that has been reserved at the lunch box store, it will not always be noticeable by the customer, which is not preferable. . However, this is often the case for customers who are familiar with the store clerk.

  As described above, if the words recognized by the voice recognition technology are displayed or printed on the screen as they are, there may be a problem.

  An object of the present invention is to prevent a predetermined word recognized by a voice recognition function from being output as it is visible.

  An object of the present invention is to make it easy to organize / manage words that are output in a visually recognizable manner with a sense of unity.

  An object of the present invention is to prevent a rude wording from being output in a visible manner at a location where honorifics should be used.

  The present invention provides a speech recognition result output device that is equipped with a speech recognition function and outputs a speech recognition-recognized recognition word so as to be visible, a word list that associates output characters with a recognized recognition word that is recognized by speech, and a speech recognition If it is determined that a list search means for searching the word list based on the recognized word words and a recognized word word recognized by the list search means in the word list is registered, Output means for extracting an output character associated with the recognized wording and outputting it in a visually recognizable manner.

  Therefore, only when the recognized word recognized by speech is registered in association with the output character in the word list, the output character associated with the recognized word is extracted from the word list and output so as to be visible. Is done. As a result, without recognizing the speech recognized by the speech recognition function as it is, the same output characters are associated with the various recognized words in the word list, for example, so that the various recognized words can be matched. Can be output in a visually recognizable manner, so that the words output in a visually recognizable manner have a sense of unity, the appearance is orderly, and the organization / management becomes easy.

  The present invention provides a speech recognition result output device that is equipped with a speech recognition function and outputs a speech recognition-recognized recognition word so as to be visible, a word list that associates output characters with a recognized recognition word that is recognized by speech, and a speech recognition If it is determined that a list search means for searching the word list based on the recognized word words and a recognized word word recognized by the list search means in the word list is registered, When an output character associated with the recognized word is extracted and output so as to be visible, and when it is determined that no recognized word recognized in the word list is registered, the recognized word is used as an output character as it is. Output means for outputting in a visually recognizable manner.

  Therefore, when a recognized speech word recognized in association with an output character is registered in the word list, the output character associated with the recognized word is extracted from the word list and output in a visible manner. If the word list is not registered in association with the output character, the recognized word is output as an output character so as to be visible. As a result, the words recognized by the voice recognition function are not output so as to be visible as they are, but for example, a recognized word group having a certain meaning (“San”, “Kun”, “Chan”, etc.) By associating a standard output character (a title such as “sama”) in the word list, it is possible to prevent a rude word from being output in a visible manner at a location where the honorific should be used.

  The present invention relates to a speech recognition result output device that is equipped with a speech recognition function and outputs a speech recognition-recognized recognition word so that it can be visually recognized. Based on the wording, when it is judged that the list searching means for searching the word list and the recognized word recognition recognized in the word list by the list searching means is registered, the output of the recognized wording is prohibited. And an output unit that outputs the recognized word as it is as an output character when it is determined that the recognized word recognized by voice recognition is not registered in the word list.

  Therefore, when a recognized word recognized by speech is registered in association with an output character in the word list, output of the recognized word is prohibited and registered in association with the output character in the word list. If not, the recognized word is output as an output character so as to be visible. As a result, the words recognized by the voice recognition function are not output so as to be visible as they are, and for example, a recognized word group having a certain meaning (“San”, “Kun”, “Chan”, etc.) is actually “ When it should be output as a title such as “Sama”, the output of the recognized wording is prohibited, so it is possible to prevent the rude wording from being output in a place where the honorific should be used. become.

  According to the present invention, it is possible to prevent a predetermined word recognized by the voice recognition function from being output as it is.

  According to the present invention, it is possible to easily arrange / manage the words that are output in a visually recognizable manner with a sense of unity and an orderly appearance.

  According to the present invention, it is possible to prevent a rude wording from being output in a visible manner at a location where honorifics should be used.

[First embodiment]
A first embodiment of the present invention will be described with reference to FIGS. In the present embodiment, a portable printer is applied as a voice recognition result output device.

  1 is an external perspective view showing the voice memo printer 1 from the label discharge side, FIG. 2 is an external perspective view showing the voice memo printer 1 from the operator mounting side, and FIG. 3 is a horizontal view showing the internal structure of the voice memo printer 1. It is sectional drawing.

  As shown in FIGS. 1 to 3, a printer main body 1a of a voice memo printer 1 which is a portable portable printer includes a case 2 with one side opened, and a cover 3 for opening and closing the opened side of the case 2. It is made up of. The cover 3 is rotatably supported by a fulcrum shaft 4 provided on the case 2. The case 2 is formed with a hopper 6 for storing the long recording paper 5 wound in a roll shape with the cover 3 closed. In the present embodiment, the recording paper 5 is obtained by attaching a large number of labels 5b to the mount 5a at equal intervals, but other recording paper may be used. The label 5b is coated with a glue having a weak adhesive force, and can be used as a sticky note P (see FIGS. 8, 11, and 14) after the printing is issued.

  In such a case 2, a paper guide 7 extending from the bottom of the hopper 6 toward the cover 3 is provided. A portion of the paper guide 7 near the cover 3 has a rotatable platen 8 and A label peeling body 9 along the longitudinal direction of the platen 8 is disposed.

  As shown in FIG. 3, a head support 11 having a thermal head 12 is provided on the inner surface of the cover 3 (on the hopper 6 side) so as to be rotatable around a support shaft 11a. The head support 11 is biased in one direction by a leaf spring 13, and the thermal head 12 comes into contact with the platen 8 with the cover 3 closed. That is, the printing unit 14 is formed by the platen 8 and the thermal head 12.

  Further, on both sides of the free end side of the cover 3, pinch rollers 16 that are pressed against the platen 8 by the urging force of the spring 15 are rotatably provided. Further, the cover 3 is formed with a label discharge port 17 that is disposed between the thermal head 12 and the pinch roller 16 and discharges the label 5b, and a paper presser 18 that presses the floating of the recording paper 5 in the hopper 6. ing. The case 2 is formed with a mount discharge port 19 for discharging the mount 5 a between the free end of the cover 3.

  On the upper surface of the case 2, a power switch 20 that declares ON / OFF of power supply from the battery 10 (see FIG. 3), a feed switch 21 that performs printing on the label 5 b, a lid 22, and a light receiving window that receives infrared rays. 23 is provided. The lid portion 22 opens and closes when the battery 10 is attached to and detached from the battery storage portion 30 (see FIG. 3) provided to be opened on the upper surface that is one surface of the case 2. Further, locking claws 24 are slidably provided on both sides of the cover 3 (see FIG. 1). These locking claws 24 are urged outward to be locked to the case 2, and when the cover 3 is opened, the locking claws 24 are slid inward as indicated by the arrow marks to engage with the case 2. Release the stop state.

  A built-in microphone 52 is provided on the same surface of the case 2 as the label discharge port 17. The voice memo printer 1 according to the present embodiment is equipped with a voice recognition function, and the built-in microphone 52 is used when executing the voice recognition function.

  In addition, an LED 56 is disposed on the upper surface of the case 2. The voice memo printer 1 of the present embodiment can notify the operator of the operation state of the voice memo printer 1 by turning on or blinking the LED 56.

  Further, as shown in FIG. 2, an arc surface 25 is formed on one surface of the printer body 1a opposite to the cover 3 so as to be in close contact with the operator's waist. On the other hand, a non-slip 26 for reducing slippage and a belt hook 27 which is hooked on the operator's belt so as to face the non-slip 26 are formed.

  With such a configuration, when the battery 10 is correctly stored in the battery storage unit 30, the terminal of the battery storage unit 30 and the terminal of the battery 10 come into contact with each other while the power switch 20 is ON. Thus, power is supplied from the battery 10 to each part such as the thermal head 12 that requires power supply.

  In such a voice memo printer 1, when the recording paper 5 is set, the cover 3 is opened, the recording paper 5 wound in a roll shape is stored in the hopper 6 of the printer main body 1a, and the cover 3 is opened. In this state, the front end of the recording paper 5 is pulled out to a position covering the platen 8 and the label peeling body 9 and the cover 3 is closed. As a result, as shown in FIG. 3, the leading end portion of the mount 5a of the recording paper 5 is pressed against the platen 8 by the thermal head 12 and the pinch roller 16, and the pull-out path of the mount 5a is formed by the label peeling member 9. The recording paper 5 is bent at an acute angle and the recording paper 5 is prevented from floating from the bottom surface of the hopper 6. The printer main body 1a on which the recording paper 5 is set can be used by placing it on a desk, but it can also be used even when it is usually worn on the operator's waist.

  Next, the connection of the control system of each part of the voice memo printer 1 will be described with reference to FIG. The voice memo printer 1 includes a CPU (Central Processing Unit) 41 that centrally controls each unit. The CPU 41 stores a ROM (Read Only Memory) in which fixed data such as a program executed by the CPU 41 is written. 42, a RAM (Random Access Memory) 43 in which variable data such as work data is renewably written, and a flash memory 44 for registering various information are connected via a bus line 45. Then, a thermal head driver 46 for driving the thermal head 12, a motor driver 48 for driving a motor 47 connected to the platen 8, a sensor circuit 50 to which various sensors 49 are connected, and a cover open that is turned on and off by opening and closing the cover 3. A switch circuit 54 to which the switch 51, the power switch 20 and the feed switch 21 are connected, an infrared interface 55, and a lighting control circuit 57 to which the LED 56 is connected are connected to the CPU 41. As described above, the circuit shown in FIG. 4 is formed on a substrate (not shown) provided inside the printer main body 1a. The infrared interface 55 is disposed inside the light receiving window 23 described above. The interface is denoted as I / F in the figure.

  The CPU 41 is connected with a voice input CODEC 53. A built-in microphone 52 is connected to the audio input CODEC 53. The audio input CODEC 53 converts audio analog data input from the built-in microphone 52 into audio digital data and outputs the audio digital data to the CPU 41.

  Further, a speech recognition engine 58 is connected to the CPU 41. The voice recognition engine 58 analyzes voice digital data input from the built-in microphone 52 and generated by the voice input CODEC 53, and converts human voice into text. Such a speech recognition engine 58 includes, for example, an acoustic dictionary 59 in which acoustic features (phonemes) of small units (phonemes) of human speech are registered, and a language pattern dictionary 60 in which language features of words to be recognized are registered. Voice recognition is performed using.

  The words to be recognized by speech registered in the language pattern dictionary 60 of the present embodiment are limited to specific applications. Since a specific word is often issued in a specific application, the language pattern dictionary 60 can be configured at low cost by registering only the words focused on the specific application in the language pattern dictionary 60 in this way. . Specifically, a list of conversations and utterance languages that will be used in the application to be used is collected and used as a use language table (not shown) for each application. For each language registered in this use language table for each application, the frequency of the language is analyzed and separated into speech features (phoneme information) and language features (phoneme series information). The language features separated in this way are registered in the language pattern dictionary 60.

The acoustic dictionary 59 is used as a dictionary related to voice recognition in general, not by use. The principle of speaking is
(1) “My throat trembles”
(2) “Passing through oral cavity / nasal cavity”
Therefore, the acoustic dictionary 59 stores information for specifying the shapes (1) and (2) from the voice frequency.

  As shown in FIG. 5, the speech recognition engine 58 having such a configuration performs frequency conversion on the speech digital data input from the built-in microphone 52 and generated by the speech input CODEC 53, and analyzes and compares the data. An acoustic feature is calculated based on the acoustic dictionary 59 in the unit 58b (voice feature extraction means). At this stage, only the shapes (1) and (2) described above can be specified, and any of the 50 sounds cannot be specified yet. Therefore, from the words registered in the language pattern dictionary 60, a word whose language feature is closest to the acoustic feature of the input speech is searched for and output as a speech recognition result (language feature extraction means). By comparing with the language pattern dictionary 60 in this way, “Aiueo” or the like can be specified for the first time. It is difficult to specify when a large number of unspecified words are uttered, but if you try to narrow down to words that are uttered for a specific purpose and compare the relationship of (1) and (2) above and the characteristics of the phoneme sequence waveform, The possibility of misrecognition can be suppressed as much as possible, and speech recognition is possible with such a simple mechanism.

  The language pattern dictionary 60 can be updated from an external device by connecting an external device (such as a personal computer) (not shown) to the voice memo printer 1 via the infrared interface 55. Further, the contents of the language pattern dictionary 60 are changed by exchanging the language pattern storage chip (dictionary) for storing the language pattern dictionary 60 or rewriting the registered contents by downloading the language pattern dictionary 60 from an external device (such as a personal computer) (not shown). It is also possible to change for each specific application. When a new language pattern dictionary 60 is downloaded via the infrared interface 55, the old language pattern dictionary 60 is deleted.

  In addition, in the voice memo printer 1 of the present embodiment, a print word list 70 as shown in FIG. The print word list 70 is for specifying a character to be printed in advance, and a print character is recognized as a recognition word predicted from a word recognized by the voice recognition engine 58 that will be inputted to print this character. This is a print dictionary that associates (output characters). According to the example shown in FIG. 6, the print characters “Hokkaido salmon lunch” are associated with recognition words such as “Hockey salmon”, “Hockey salmon”, and “Hockey salmon ben”.

  Next, of the functions that the control program stored in the ROM 42 built in the voice memo printer 1 causes the CPU 41 to execute, the characteristic functions provided in the voice memo printer 1 of the present embodiment will be described.

  Here, the voice printing process executed by the CPU 41 of the voice memo printer 1 will be described. FIG. 7 is a flowchart showing the flow of the voice printing process. As shown in FIG. 7, when digitized voice is input (Y in step S1), the process proceeds to step S2, and voice recognition processing by the voice recognition engine 58 is executed.

  Next, it is determined that the word is registered in the language pattern dictionary 60 in the voice recognition process, and based on the recognized word word that is voice-recognized by searching for the word whose language feature is closest to the acoustic feature of the input voice, The list 70 is searched (step S3: list search means).

  If a recognized word recognized by voice is registered in the printed word list 70 (Y in step S4), a print character associated with the recognized word is extracted from the printed word list 70 (step S5) and printed. It outputs to the part 14 and prints (step S6: output means). Here, FIG. 8 is a plan view showing an example of the issued sticky note P. FIG. As shown in FIG. 8, on the sticky note P, the text “Hokkaido Salmon Bento” in the case of saying “Hokkai salmon” is printed.

  On the other hand, when the recognized word recognized by the voice is not registered in the printed word list 70 (N in step S4), the process is stopped and the process returns to step S1 to wait for the next digitized voice input.

  For example, in a bento restaurant, you may want to print “Hokkaido bowl lunch”, but it is assumed that the input phrase varies from person to person. Even when the input words are unified, it is not always possible to correctly speak up to the pronunciation of “salmon” and “salmon”. Also, even if you can speak correctly by practicing, if you are in a busy situation, you may omit words or return words. However, according to the voice memo printer 1 of the present embodiment, “Hokkaido salmon lunch” is printed on various generated voices (recognition words) such as “hokkaisake”, “hokkaishake”, “hokkaido salmon ben”, etc. By specifying the wording, the memos printed on the sticky note P have a sense of unity, the appearance is orderly, and the organization / management becomes easy.

  Note that these are excluded from the printed word list 70 as uttered speech (recognition word) so that selection is not performed only by pronounced “salmon” and “salmon”. The reason is that if the pronunciation of “salmon” is mixed in the utterance, such as “alcohol”, “if you scream” or “avoid”, it will be accepted as “Hokkaido salmon lunch”. However, if it is determined in operation that there is no voice input as in the case of the lunchbox conversation, “salmon” and “salmon” may be added to the printed word list 70 as voices (recognition word).

  As described above, according to the present embodiment, only when the recognized word recognized by voice is registered in association with the output character in the printed word list 70, the word is associated with the recognized word from the printed word list 70. The output characters are extracted and output (printed) so as to be visible. As a result, without recognizing and recognizing the speech recognized by the speech recognition function as it is, for example, by associating the same output characters in the word list with the various recognized words, Since the same text can be output (printed) so as to be visible, the text output (printed) so as to be visible has a sense of unity, looks neat, and is easy to organize / manage.

[Second Embodiment]
A second embodiment of the present invention will be described with reference to FIGS. In addition, the same part as 1st Embodiment mentioned above is shown with the same code | symbol, and description is also omitted. This embodiment is different from the first embodiment described above in the print word list stored in the flash memory 44 and the flow of voice recognition processing.

  FIG. 9 is a flowchart showing the flow of voice printing processing in the voice memo printer 1 of the present embodiment. As shown in FIG. 9, when digitized voice is input (Y in step S11), the process proceeds to step S12, and voice recognition processing by the voice recognition engine 58 is executed.

  Next, it is determined that the word is registered in the language pattern dictionary 60 in the voice recognition process, and based on the recognition word that is voice-recognized by searching for a word whose language feature is closest to the acoustic feature of the input speech, FIG. Is retrieved (step S13: list retrieval means). The print word list 71 is for specifying in advance a character to be printed, and a print character is recognized as a recognition word predicted by the voice recognition engine 58 to be inputted to print this character. Is a print dictionary that associates. According to the example shown in FIG. 10, a print character “sama” is associated with recognition words such as “san”, “kun”, and “chang”.

  If a recognized word recognized by speech is registered in the printed word list 71 (Y in step S14), the print characters of the registered recognized word are extracted from the printed word list 71 (step S15), and the printing unit 14 Is output and printed (step S16). Here, FIG. 11 is a plan view showing an example of the issued sticky note P. FIG. As shown in FIG. 11, the sticky note P is printed with the text “Saito-sama” when “Saito Chan” is uttered.

  On the other hand, if the recognition word recognized by voice recognition is not registered in the print word list 71 (N in step S14), the recognition word is directly used as a print character, and is output to the printing unit 14 for printing (step S16: output means). ).

  For example, if a customer's name is abandoned or becomes “Saito-chan” in a reservation memo for a bento that has been reserved at a bento store, it will not always be noticeable by the customer. . However, this is often the case for customers who are familiar with the store clerk. For this reason, even if it is a convenient printer having the feature of making a voice as a memo as it is, if the voice is printed as it is, it becomes a disadvantage. However, according to the voice memo printer 1 of the present embodiment, by specifying the print word “sama” for the generated voice (recognition word) such as “san”, “kun”, “chang”, etc., the honorific It is possible to prevent a rude wording from being printed at a place where the character is to be used.

  As described above, according to the present embodiment, when a recognized word recognized by voice is registered in association with an output character in the printed word list 71, it is associated with the recognized word from the printed word list 71. If the output character is extracted and output (printed) so as to be visible, and if it is not registered in the printed word list 71 in association with the output character, the recognized word is directly output as an output character. (Printed). Thus, for example, a recognition word group having a certain meaning (“San”, “Kun”, “Chan”, etc.) without outputting (printing) the speech recognized by the voice recognition function as it is. By associating a standard output character of that meaning (a title such as “sama”) in the print word list 71, it is possible to prevent a rude word from being output (printed) in a place where the honorific should be used. It becomes possible.

[Third embodiment]
A second embodiment of the present invention will be described with reference to FIGS. In addition, the same part as 1st Embodiment mentioned above is shown with the same code | symbol, and description is also omitted. This embodiment is different from the first embodiment described above in that a print prohibition word list is provided instead of the print word list stored in the flash memory 44 and the flow of the speech recognition process is different. is there.

  FIG. 12 is a flowchart showing the flow of the voice printing process in the voice memo printer 1 of the present embodiment. As shown in FIG. 12, when digitized voice is input (Y in step S21), the process proceeds to step S22, and voice recognition processing by the voice recognition engine 58 is executed.

  Next, it is determined that the word is registered in the language pattern dictionary 60 in the voice recognition process, and based on the recognition word that is voice-recognized by searching for the word whose language feature is closest to the acoustic feature of the input speech, FIG. Is searched (step S23: list search means). The print prohibition word list 72 is a print dictionary for registering print prohibition words among the recognition words predicted from the words recognized by the voice recognition engine 58. According to the example shown in FIG. 13, recognition words such as “San”, “Kun”, and “Chan” are registered as print prohibition words.

  If the recognized word recognized by voice in the print prohibition word list 72 is registered as a print prohibition word (Y in step S24), the recognition word is deleted (step S25), and is output to the printing unit 14 for printing. (Step S26: Output means). Here, FIG. 14 is a plan view showing an example of the issued sticky note P. FIG. As shown in FIG. 11, the sticky note P is printed with the text “Saito” when “Saito Chan” is uttered.

  On the other hand, if a recognized word recognized by voice recognition is not registered in the print prohibition word list 72 (N in step S24), the recognized word is directly used as a print character, and is output to the printing unit 14 for printing (step S26).

  As described above, according to the present embodiment, when a recognized recognition word is registered in association with an output character in the print prohibition word list 72, the output (printing) of the recognition word is prohibited. If the print prohibited word list 72 is not registered in association with the output character, the recognized word is output as an output character so as to be visible. As a result, the words recognized by the voice recognition function are not output (printed) so that they can be seen as they are, but, for example, a recognized word group having a certain meaning (“San”, “Kun”, “Chan”, etc.) is actually used. If it should be output as a title such as “Sama”, the output (printing) of the recognition word is prohibited, so that rude text can be output (printed) in a place where the honorific should be used. It becomes possible to prevent that.

  In each embodiment, the output means outputs a print character (output character) to the printing unit 14 for printing, but the present invention is not limited to this. For example, when a display device is applied as the speech recognition result output device, the output means may output display characters (output characters) to the display device and display them on the screen.

1 is an external perspective view showing a voice memo printer according to a first embodiment of the present invention from a label discharge side. It is an external appearance perspective view which shows a voice memo printer from the operator mounting side. It is a horizontal sectional view showing the internal structure of the voice memo printer. It is a block diagram which shows the connection of the control system of each part of a voice memo printer. It is a block diagram which shows the structure of a speech recognition engine. It is a schematic diagram which shows a printing word list. It is a flowchart which shows the flow of an audio | voice printing process. It is a top view which shows an example of the issued sticky note paper. It is a flowchart which shows the flow of the audio | voice printing process of 2nd embodiment of this invention. It is a schematic diagram which shows a printing word list. It is a top view which shows an example of the issued sticky note paper. It is a flowchart which shows the flow of the audio | voice printing process of 3rd embodiment of this invention. It is a schematic diagram which shows a printing prohibition word list. It is a top view which shows an example of the issued sticky note paper.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Voice recognition result output apparatus, 14 ... Printing part, 70, 71, 72 ... Word list

Claims (5)

In the speech recognition result output device that is equipped with a speech recognition function and outputs the speech recognition recognition wording so as to be visible,
A word list that associates output characters with the recognized recognition words that are recognized by voice,
A list search means for searching the word list based on a recognized word recognized by voice;
When it is determined that a recognized word recognized in the word list is registered in the word list by the list search means, an output character associated with the recognized word is extracted from the word list and output so as to be visible Output means for
A speech recognition result output device comprising: In the speech recognition result output device that is equipped with a speech recognition function and outputs the speech recognition recognition wording so as to be visible,
A word list that associates output characters with the recognized word recognition that is recognized by voice,
A list search means for searching the word list based on a recognized word recognized by voice;
When it is determined that a recognized word recognized in the word list is registered in the word list by the list search means, an output character associated with the recognized word is extracted from the word list and output so as to be visible And, if it is determined that the recognized speech recognized in the word list is not registered, an output means for outputting the recognized word as it is as an output character so as to be visible,
A speech recognition result output device comprising: In the speech recognition result output device that is equipped with a speech recognition function and outputs the speech recognition recognition wording so as to be visible,
A word list for storing the recognized word words to be recognized,
A list search means for searching the word list based on a recognized word recognized by voice;
When it is determined by the list search means that a recognized word recognized in the word list is registered in the word list, output of the recognized word is prohibited, and a recognized word recognized in the word list is registered. When it is determined that there is no output means for outputting the recognition word as it is as an output character so as to be visible,
A speech recognition result output device comprising: The output means outputs an output character to a printing unit and prints it.
The speech recognition result output device according to any one of claims 1 to 3. The output means outputs an output character to a display device and displays the screen.
The speech recognition result output device according to any one of claims 1 to 3.

Images