JP2000242464A - Processor and method for processing voice information and storage medium stored with voice information processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically decide which of processing contents corresponding to a voice command and other processing contents are executed according to voice information by providing a voice command execution part and a voice information processing part which execute processing contents according to whether or not the voice information matches the voice command. SOLUTION: The voice information processor is constituted by providing a voice recognition dictionary 14 containing voice information corresponding to voice and a voice command table previously stored with voice commands corresponding to the voice information. Voice information is recognized from inputted voice according to the voice recognition dictionary and compared with voice commands in the voice command table 17 to check whether or not there is a matching voice command. When a matching voice command is found, a voice command execution part 18 executes the processing contents corresponding to the voice command. When no matching command is found, a voice information processing part executes the other processing contents set specially for the voice information.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is applied to a word processor, a personal computer, various information processing apparatuses, and the like, and stores a voice information processing apparatus and method for executing document input and various applications by voice input, and a voice information processing program. Related to a storage medium.

[0002]

2. Description of the Related Art In recent years, with the development of voice recognition technology, a voice command of a specific speaker or an unspecified speaker is recognized from voice information, and commands are issued directly to a personal computer by voice commands, or text information is output from voice information. It has been converted to information and used as document input.

[0003] However, at present, a speech recognition device that enables a human to have a natural conversation with a machine has not been realized. One of the causes is a problem of fluctuation of utterance in natural dialogue. For example, words that have no meaning in themselves, such as "um" or "um", could not be correctly recognized. As a conventional technique for solving this problem, for example, according to Japanese Patent Application Laid-Open No. 5-197389, a time series of voice feature parameters is obtained from an input voice signal, and a voice feature vector obtained from the time series is prepared in advance. Using the recognized recognition target words, syntactic analysis, and semantic analysis,
2. Description of the Related Art There has been proposed a speech recognition apparatus that recognizes natural utterances such as words that have no meaning in themselves, such as "um" and "um".

Another problem is that sentences having different meanings depending on the word order are erroneously recognized as sentences having the same meaning. As a conventional technique for solving this problem, for example, Japanese Patent Laid-Open No.
According to the description of Japanese Patent No. 6994, a sentence template in which words to be recognized, meanings of words, and groups of words are described according to the order of appearance in the input speech, and words in which meanings of words and groups of words are described 2. Description of the Related Art There has been proposed a speech recognition apparatus that accurately recognizes expressions having a high degree of freedom, such as word order, using a dictionary.

In recent years, network services using personal computers as terminals have been actively used. However, the user interface of personal computer communication terminals has a problem that it is difficult to learn commands and it takes time to move between menu items. there were. As a conventional technique for solving this problem, for example, according to Japanese Patent Application Laid-Open No. 8-194600, a recognition result obtained from a voice input is converted into a data format based on the communication protocol of the network service, and the network service is provided to the network service. Access by voice input
2. Description of the Related Art There has been proposed an easy-to-use voice input terminal device by configuring an interface and using voice input.

[0006]

The above-mentioned JP-A-5-19
JP-A-7389 and JP-A-6-186994 provide a speech recognition technique for improving the recognition accuracy of speech information. JP-A-8-194600 discloses a speech recognition technique used as a user interface access by speech input. Is provided.

However, the speech information recognized as speech is converted into a voice command and an application is executed according to the voice command, a document is created by converting the text information into text information, or the voice information is directly converted into a voice memo. It can be used for multiple functions. When inputting voice information to a document processing apparatus, the above-described conventional voice recognition technology is not configured to correspond to multiple functions by selectively using voice commands and text information from the recognized voice information.

The present invention has been made in consideration of the above circumstances. For example, voice information input by voice is converted into voice commands to execute an application in accordance with the voice commands, or converted into text information. The present invention provides an audio information processing apparatus and method, and a storage medium storing an audio information processing program, which can create a document by using the audio information as it is as a voice memo for multiple functions.

[0009]

According to the present invention, there is provided a voice recognition dictionary storing voice information corresponding to voice, a voice command table storing voice commands corresponding to voice information in advance, and a voice input unit for inputting voice. A voice recognition unit that recognizes voice information from the input voice based on a voice recognition dictionary; a voice command comparison unit that compares whether voice information matches a voice command in a voice command table; When the voice command matches, the voice command execution unit executes the processing content corresponding to the voice command, and when the voice information does not match the voice command, executes the processing content separately set for the voice information An audio information processing apparatus comprising: an audio information processing unit.

[0010] In the present invention, the audio input section can be composed of a microphone, an amplifier, a filter, and the like.
Further, the voice recognition unit, the voice command comparison unit, and the voice information processing unit may be configured by a computer including a CPU, a ROM, a RAM, and an I / O port. The voice recognition dictionary and the voice command table can be configured by a storage device such as a ROM, a floppy disk, and a hard disk.

According to the present invention, it is automatically determined whether to execute the processing content corresponding to the voice command or to execute the processing content set separately based on the voice information input from the voice input unit. can do. For this reason,
There is no need to set the target processing content to be executed before processing the input audio information.

[0012]
| If the voice information processing unit acquires voice information that does not match a voice command during a word search for document creation, the voice information may be converted into text information as a search keyword. According to this configuration, word search processing for document creation can be performed using voice information that does not match a voice command as a search keyword.

When the voice information processing unit acquires voice information that does not match a voice command in the voice command table during document creation, the voice information is converted into text information as words and input to the document being created. It may be. According to this configuration, voice information that does not match the voice command can be input to the document as a word.

When the voice information processing unit acquires voice information that does not match the voice command during the voice memo processing, the voice information may be directly input to the voice memo without being converted into text information. According to this configuration, voice information that does not match the voice command can be input as a voice memo.

[0015] The speech information processing unit is configured to, when converting speech information acquired during word search for document creation into text information as a search keyword, delete words having no meaning contained in the converted text information. You may. According to this configuration, it is possible to perform a search process using a speech recognition word as a keyword while excluding nonsense words such as connective words as targets.

The speech information processing unit converts the speech information acquired during document creation into text information as words.
A configuration may be adopted in which the end of a sentence is determined, converted into punctuation marks, and input into the document being created. According to this configuration, it is possible to input a punctuation mark by determining the end of a sentence during input of a document by voice.

[0017] The voice information processing section may be configured to delete the text information from the document when the text information input during document creation matches the voice command.
According to this configuration, it is possible to delete the text information corresponding to the voice command unnecessary for the document from the document in which the voice input information including the voice command is input as the text information.

When the voice information input during the voice memo processing includes a voice command, the voice information processing section may delete the voice information from the voice memo.
According to this configuration, it is possible to delete voice information corresponding to voice commands unnecessary for the voice memo from the voice memo to which voice information including the voice command is input.

According to another aspect of the present invention, voice information corresponding to voice is stored in a voice recognition dictionary, voice commands corresponding to voice information are stored in a voice command table in advance,
A voice is input using a voice input unit, voice information is recognized from the input voice based on a voice recognition dictionary using a voice recognition unit, and the recognized voice information and voice are recognized using a voice command comparison unit. Compare whether or not the voice command in the command table matches, and if the voice information and the voice command match, execute the processing content corresponding to the voice command using a voice command execution unit, and If the voice command does not match, using the voice information processing unit,
A voice information processing method is provided, wherein a separately set processing content is executed for voice information.

[0020]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail based on an embodiment shown in the drawings. The present invention is not limited by this.

FIG. 1 is a block diagram showing the configuration of an information processing apparatus according to one embodiment of the present invention. In FIG. 1, reference numeral 1 denotes a CPU of a computer that controls each unit of the audio information processing apparatus of the present invention by a control program. Reference numeral 2 denotes a display unit including a CRT display, a liquid crystal display (LCD), a plasma display, and the like, and displays input documents and input instruction information. Reference numeral 3 denotes a keyboard 4 for inputting information from an operator and instructions for printing, a mouse 5, a microphone 6 for inputting voice, and a voice input unit including an A / D conversion circuit for converting a voice signal into voice data. The input part to be performed is shown.

Reference numeral 23 denotes a printing unit including a thermal printer and a laser printer, which prints a document. Reference numeral 24 denotes a communication unit for communication connection with another information processing terminal on a communication line. Reference numeral 25 denotes an audio output unit including a speaker, a D / A conversion circuit, and the like, and reproduces audio information (audio data) recorded in an audio memo buffer. Reference numeral 26 denotes a bus for transferring addresses, control program data, voice data (voice commands, voice texts) and the like.

Reference numeral 7 denotes a RAM which is a readable / writable memory in the information processing apparatus and an RO which is a read-only memory.
1 shows an information storage unit including an M and a magnetic storage device. As a RAM of the information storage unit, a search keyword buffer 9 for storing and expanding a program or storing a search keyword, a document buffer 10 for storing a text document, a voice memo buffer 12 for storing voice information as it is, It comprises a speech recognition word dictionary storage unit 15 for storing speech recognition words, an area functioning as a speech input buffer (speech information storage unit) 19 for storing speech data input by speech input, and the like.

The ROM of the information storage unit functions as a voice recognition dictionary 14 in which voice recognition data for recognizing digital voice data and converting it into code data is stored in advance, and a voice command table 17 in which voice commands are stored in advance. Data to be stored.

Further, the ROM functions as a keyword extracting unit 8 for extracting a keyword in a search at the time of document creation and storing the keyword in a search keyword buffer 9, and stores voice data input with reference to a voice recognition dictionary 14. Speech recognition word dictionary storage unit 1 after converting to speech recognition word
5, a voice command comparison program that functions as a voice command comparison unit 16 that compares the voice recognition word stored in the voice recognition word storage unit 15 with the voice command table 17, A program that functions as the voice command execution unit 18 that executes the voice command is stored.

The voice recognition unit 13 can use several voice recognition methods. For example, an audio signal input from an audio input unit such as a microphone is converted into a digital signal, and this digital signal is subjected to FFT, filter analysis, L
Analysis processing such as PC analysis and cepstrum analysis is performed to generate a speech feature parameter sequence. The speech recognition unit 13 compares the generated speech feature parameter sequence with a speech recognition dictionary 14 that stores a speech feature pattern of a keyword that is a predetermined recognition target word.

Also, there is speech recognition by a word spotting method in which a speech feature parameter sequence generated by a speech input unit is continuously collated with a speech recognition dictionary at certain fixed intervals.

20 is a RAM backed up by a battery,
A program memory constituted by a nonvolatile memory composed of an EEPROM is shown, and stores a control program of the CPU 1, various data, and the like. Reference numeral 21 denotes a storage medium including a floppy disk, a hard disk, an MD, and a CD-ROM. The storage medium 21 stores data of a voice information processing program, a voice recognition dictionary, and a voice command table of the present invention. .

Reference numeral 22 denotes a storage medium reading section. The storage medium reading section 22 reads the voice information processing program of the present invention and various data stored in the storage medium 21 as necessary, and installs them in the program memory 20. Can be. The data of the created document or voice memo is stored in the storage medium 2
1 and can be used by an external information processing device. Further, the voice information processing program of the present invention may be transmitted to an external information processing device via the communication unit 24.

According to another aspect of the present invention, a voice recognition dictionary storing voice information corresponding to voice, a voice command table storing voice commands corresponding to voice information in advance, and a voice input unit for inputting voice And make the computer of the voice information processing device with voice information recognize the voice information from the input voice based on the voice recognition dictionary, and compare the recognized voice information with the voice command in the voice command table. If the voice information matches the voice command, the process corresponding to the voice command is executed. If the voice information does not match the voice command, the process set separately for the voice information is executed. A storage medium 21 storing a voice information processing program characterized by the following is provided.

With this configuration, the voice information processing program of the present invention is stored in the storage medium 21 and installed in the program memory 20 as necessary, thereby realizing the voice information processing apparatus of the present invention even with an external information processing apparatus. be able to.

FIG. 2 is a schematic flowchart showing the procedure of the application selecting process of the present embodiment. FIG. 10 is a diagram illustrating an example of an application selection screen according to the present embodiment. The application selection process shown in FIG. 2 is executed by selecting an application 10-
Select 1 to 10-6. S101: Keyboard application to be executed
Select by voice input from mouse, microphone, etc. S102: In FIG. 10, when the “document creation” application 10-1 is selected, the process proceeds to S103. S103: Execute document creation processing (see FIG. 3).

S104: If the "voice input" application of 10-4 has been selected, the process proceeds to S105. S105: Execute voice input processing (see FIGS. 5 and 6). S106: If the “voice memo” application of 10-5 has been selected, the process proceeds to S107. S107: Execute voice memo processing (see FIG. 7). S108: When an application such as "call" in 10-2, "graphic" in 10-3, and "auxiliary" in 10-6 is selected, other processing is executed.

FIG. 11 is a diagram showing an example of inputting a document on the document creation screen of this embodiment. For example, the document creation screen shown in FIG. 11 is a screen for inputting and editing a document by inputting with a keyboard or a mouse. On the screen, a voice command or a keyword at the time of search can be input by a voice input unit such as a microphone.

FIG. 3 is a detailed flowchart showing the procedure of the document creation process in S103 of FIG. In FIG. 3, S202: Recognize voice information input by voice on the document creation screen of FIG. 11 as a voice recognition word. S203: The voice command comparing unit 16 compares whether or not the voice recognition word obtained by the voice recognition matches the voice command. If they match, the process moves to S205; otherwise, the process moves to S206.

FIG. 19 is a diagram showing a comparison example between the voice command table of the present embodiment and voice recognition words. As shown in FIG. 19, for example, when the input speech recognition word is “save”, the speech recognition word in the speech recognition word buffer 15 matches the speech command in the speech command table of 19-1 to 19-7. Are compared in order. S204: It is checked whether or not it matches the voice command of the voice command table 17 stored in the memory in advance such as saving or printing. Voice command (eg, "Save")
When it matches, it moves to S205. If not (for example, “at the master”), the process proceeds to S206.

S205: The voice command execution unit 18 executes "save" which is a voice command. S206: Extract a search keyword (see FIG. 4). FIG. 20 is a diagram showing an example of deleting a voice recognition word input by voice according to the present embodiment. For example, as shown in FIG. 20, when the input speech recognition word is “Shoshiri” and does not match the speech command in the speech command table, a search keyword is extracted. S207: Extracted search keyword “Shashiri” Perform a search with. FIG. 12 is a diagram illustrating an example of a search process on the document creation screen according to the present embodiment. As shown in FIG. 12, a search keyword "shiwashi" input by voice is searched and executed.

FIG. 4 is a detailed flowchart showing the procedure of the search keyword extraction process in S206 of FIG. In FIG. 4, S302: The speech recognition word obtained in S202 of FIG. 3 is read. S303: For example, as shown at 20-1 in FIG. 20, "at the master" held in the speech recognition word is divided into minimum word units.

S304: Connected words are extracted from the speech recognition words by syntactic analysis used in kana-kanji conversion of a Japanese word processor or the like (see 20-3 in FIG. 20). S306: The meaningless word connecting word “de” is deleted from the input speech recognition word (see 20-5 in FIG. 20). S307: “Shoshi”, a search keyword used in the search, is determined (see 20-4 in FIG. 20).

FIG. 5 is a detailed flowchart showing the procedure (1) of the voice input process in S105 of FIG. In FIG. 5, S402: When creating a document by voice input, the input voice is converted into a voice recognition word by a voice recognition unit. S403: The speech recognition word obtained by the speech recognition is compared with the speech command in the speech command table. S404: It is checked whether or not it matches the voice command in the voice command table. When the voice command matches, S4
Move to 05. Otherwise, the process moves to S406. S405: Execute a voice command.

S406: If the voice command does not match the voice command in the voice command table, the text information (character string) converted from the input voice recognition word is used for document input. FIG. 13 is a diagram showing a document input example (1) by voice input according to the present embodiment. As shown in FIG. 13, first, when the voice recognition word input by voice is “this year”,
"This year" is displayed in the document input display area 13-3. Reference numeral 13-1 denotes a document creation screen by voice input. 13-2 indicates a cursor position.

FIG. 14 is a diagram showing a document input example (2) by voice input according to the present embodiment. As shown in FIG. 14, the voice information input by voice is sequentially converted into the voice recognition words converted by voice recognition. If there is, the display area 14-3 of the document input will indicate that "you have enjoyed picking the ginkgo berry and enjoying the chawanmushi. Reference numeral 14-1 denotes a document creation screen by voice input. 14-2 indicates a cursor position.

S407: Subsequently, it is checked whether or not the speech recognition word which is inputted by speech and converted into speech information by speech recognition is "ten" or "maru". If so, S
Move to 408. Otherwise, the process moves to S412. S408: If the voice recognition word is "ten", the words before and after "ten" are determined and it is checked whether or not it is the position of the reading point. S409: It is checked whether or not it is the position of the reading point ",".

FIG. 15 is a diagram showing a document input example (3) by voice input according to the present embodiment. FIG. 15 particularly shows an example of inserting a reading point into a document. FIG. 21 is a diagram illustrating an example of processing for inserting punctuation marks into the document buffer according to the present embodiment. For example, as shown at 15-2 in FIG. 15, if the word appears at the end of the sentence and before the punctuation mark, such as "-", 21 in FIG.
As shown in -3, the reading notation "," is inserted into the document buffer and displayed on the document creation screen.

Here, the voice recognition word input by voice is "release the product to the exhibition" as in the example of 21-5 in FIG.
If it is in the middle of a word such as "ten", the converted speech recognition word is displayed. FIG. 16 is a diagram showing a document input example (4) by voice input according to the present embodiment. FIG.
As shown in FIG. 6, "the last one has been output" is displayed in the display area 16-3 as a speech recognition word which is similarly input by speech and converted by speech recognition.

S410: Subsequently, when the speech recognition word inputted by speech and converted into speech information by speech recognition is "maru", words before and after "maru" are determined, and it is determined whether or not the word is a position of a period. Find out. FIG. 17 is a diagram showing a document input example (5) by voice input according to the present embodiment. FIG. 17 particularly shows an example of inserting a period into a document. S411: For example, as shown by 17-2 in FIG.
If the word appears at the end of the sentence and before the period, such as "I ended up," the period notation "." Is inserted into the document buffer as shown at 21-4 in FIG. To be displayed.

FIG. 6 is a detailed flowchart showing the procedure (2) of the voice input process in S105 of FIG. In FIG. 6, S502: The voice recognition word (text string) input by voice input is stored in the document buffer. S503: Compare the text string stored in the document buffer with the voice command in the voice command table.

S504: It is checked whether the voice command matches the voice command in the voice command table. When the voice command matches, the process proceeds to S505. Otherwise, S506
And ends. S505: If the command matches the voice command, the input text string in the document buffer is deleted.

FIG. 18 is a diagram showing a voice memo recording example of the present embodiment. In FIG. 18, reference numeral 18-1 denotes a voice memo screen when recording (recording) an input voice as voice data in a voice memo. Reference numeral 18-2 indicates selection of a voice memo destination for recording voice data. 18-3 shows an operation screen when recording audio data. Reference numeral 18-5 denotes a start button for starting the voice memo. Reference numeral 18-6 denotes a stop button for stopping the voice memo during execution of the voice memo.

FIG. 7 is a detailed flowchart showing the procedure of the voice memo processing in S107 of FIG. FIG. 7 (1)
S602: When inputting a voice document, the voice information input by voice is converted into a voice recognition word by a voice recognition unit. S603: The speech recognition word obtained by the speech recognition is compared with the speech command in the speech command table.

S604: It is checked whether the voice command matches the voice command in the voice command table. If there is a matching voice command, the process moves to S605. Otherwise, the process moves to S606. S605: Execute the voice command. S606: If the voice command does not match the voice command in the voice command table, the input voice information remains as voice data.
Record as a voice memo

In (2) of FIG. 7, voice memo processing is performed by another means. S610: Input voice information is recorded as voice memo in voice memo buffer as voice data. S611: Compare with the voice command in the voice command table. S612: It is checked whether or not it matches the voice command in the voice command table. S613: The voice information corresponding to the voice command is deleted from the recorded voice memo buffer.

FIG. 8 is a detailed flowchart showing the procedure of the voice recognition process in S202 of FIG. 3, S402 of FIG. 5, and S602 of FIG. In FIG. 8, S702: The audio information input from the audio input unit such as the microphone 6 is stored in the audio input buffer 19. S703: The speech information stored in the speech input buffer 19 is converted by the speech recognition unit 13 into a speech recognition word. S704: The speech recognition words obtained by collation by these speech recognition units are converted into text strings. S705: The text-converted speech recognition word is stored in the speech recognition word storage unit 15.

FIG. 9 is a detailed flowchart showing the procedure of the voice command comparison process in S203 of FIG. 3, S403 of FIG. 5, and S603 of FIG. In FIG. 9, S802: The voice recognition word is read. S803: The text string converted into the voice recognition word is compared with the voice command in the voice command table.

[0055]

According to the present invention, in a personal computer or a word processor, processing content corresponding to a voice command is executed based on voice information input from a voice input unit, or processing content set separately is executed. It is possible to automatically determine whether to do so. Therefore, there is no need to set the target processing content to be executed before processing the input audio information.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an information processing apparatus according to an embodiment of the present invention.

FIG. 2 is a schematic flowchart illustrating a procedure of an application selection process according to the embodiment;

FIG. 3 is a detailed flowchart showing a procedure of a document creation process in S103 of FIG. 2;

FIG. 4 is a detailed flowchart showing a procedure of a keyword extraction process in S206 of FIG. 3;

FIG. 5 is a detailed flowchart showing a procedure (1) of a voice input process in S105 of FIG. 2;

FIG. 6 is a detailed flowchart showing a procedure (2) of a voice input process in S105 of FIG. 2;

FIG. 7 is a detailed flowchart showing a procedure of a voice memo process in S107 of FIG. 2;

FIG. 8 is a flowchart showing the operation of S202 of FIG. 3, S402 of FIG. 5, and S of FIG. 7;
6 is a detailed flowchart showing a procedure of a voice recognition process by 602.

FIG. 9 is a view showing S203 in FIG. 3, S403 in FIG. 5, and S in FIG.
603 is a detailed flowchart showing the procedure of a voice command comparison process by 603.

FIG. 10 is a diagram illustrating an example of an application selection screen according to the present embodiment.

FIG. 11 is a diagram illustrating a document input example on a document creation screen according to the present embodiment.

FIG. 12 is a diagram illustrating an example of a search process on a document creation screen according to the present embodiment.

FIG. 13 shows a document input example by voice input according to the present embodiment (1).
FIG.

FIG. 14 shows an example of a document input by voice input according to the embodiment (2).
FIG.

FIG. 15 shows a document input example by voice input according to the present embodiment (3).
FIG.

FIG. 16 shows an example of a document input by voice input according to the embodiment (4).
FIG.

FIG. 17 shows an example of a document input by voice input according to the embodiment (5).
FIG.

FIG. 18 is a diagram illustrating an example of voice memo input by voice input according to the present embodiment.

FIG. 19 is a diagram illustrating a comparative example of a voice command table and a voice recognition word according to the present embodiment.

FIG. 20 is a diagram illustrating an example of deleting a voice recognition word input by voice according to the embodiment;

FIG. 21 is a diagram illustrating an example of processing for inserting punctuation marks into a document buffer according to the present embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 CPU 2 Display part 3 Input part 4 Keyboard 5 Mouse 6 Microphone (voice input part) 7 Information storage part 8 Keyword extraction part 9 Search keyword buffer 10 Document buffer 11 Punctuation insertion part 12 Voice memo buffer 13 Voice recognition part 14 Voice recognition dictionary Reference Signs List 15 Voice recognition word storage unit 16 Voice command comparison unit 17 Voice command table 18 Voice command execution unit 19 Voice input buffer 20 Program memory 21 Storage medium 22 Storage medium reading unit 23 Printing unit 24 Communication unit 25 Voice output unit 26 Bus

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G10L 3/00 561H 571J

Claims (10)

[Claims] A voice recognition dictionary storing voice information corresponding to voice; a voice command table storing voice commands corresponding to voice information in advance; a voice input unit for inputting voice; A voice recognition unit that recognizes information based on a voice recognition dictionary, a voice command comparison unit that compares whether voice information matches a voice command in a voice command table, and a case where voice information matches a voice command A voice command execution unit that executes processing content corresponding to the voice command, and a voice information processing unit that executes processing content separately set for the voice information when the voice information does not match the voice command. A voice information processing apparatus characterized by the above-mentioned. 2. The method according to claim 1, wherein the voice information processing unit converts the voice information into text information as a search keyword when obtaining voice information that does not match a voice command during a word search for document creation. 2. The voice information processing device according to 1. 3. When the voice information processing unit obtains voice information that does not match a voice command in a voice command table during document creation, the voice information is converted into text information as words and input to a document being created. The voice information processing apparatus according to claim 1, wherein 4. When the voice information processing unit acquires voice information that does not match a voice command during voice memo processing,
2. The voice information processing apparatus according to claim 1, wherein the voice information is directly input to a voice memo without being converted into text information. 5. The speech information processing section, when converting speech information acquired during a word search for document creation into text information as a search keyword, deletes words having no meaning included in the converted text information. 3. The audio information processing apparatus according to claim 2, wherein: 6. The speech information processing section, when converting speech information acquired during document creation into text information as a word, judges the end of a sentence, converts the sentence into punctuation, and inputs it to the document being created. The audio processing device according to claim 3, wherein: 7. The voice information processing unit, when text information input during document creation matches a voice command,
4. The voice information processing apparatus according to claim 3, wherein the text information is deleted from the document. 8. The voice processing apparatus according to claim 4, wherein when the voice information input during the voice memo processing includes a voice command, the voice information processing unit deletes the voice information from the voice memo. Information processing device. 9. Voice information corresponding to voice is stored in a voice recognition dictionary, voice commands corresponding to voice information are stored in a voice command table in advance, voice is input using a voice input unit, and voice recognition is performed. The voice command is used to recognize voice information based on a voice recognition dictionary, and a voice command comparison unit is used to compare the recognized voice information with voice commands in a voice command table. When the voice information and the voice command match, the processing corresponding to the voice command is executed using the voice command execution unit, and when the voice information and the voice command do not match, the voice information And performing processing separately set on the voice information using the unit. 10. A voice information processing apparatus comprising: a voice recognition dictionary storing voice information corresponding to voice, a voice command table storing voice commands corresponding to voice information in advance, and a voice input unit for inputting voice. On the computer
When voice information is recognized based on the voice recognition dictionary from the input voice and the recognized voice information is compared with a voice command in the voice command table to determine whether or not the voice command matches the voice command. Storing a voice information processing program for executing the processing content corresponding to the voice command, and executing the processing content separately set for the voice information when the voice information does not match the voice command. Medium.