JPH1153162A - Voice processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To carry out all operations from the start to the end of application including data input and data storage with voice commands by freely registering a series of operations on a computer device in a dictionary and specifying them with vocal words and phrases. SOLUTION: A voice dictionary 6 on the side of a voice recognition device contains reading and indexes and a voice dictionary 13 on the side of the computer device contain texts and indexes corresponding to them in dictionary form. The index value of a recognized word is sent from the voice recognition device 1 to the computer device 2, which instructs an application operation part 12 to perform key operation that the index indicates, thereby performing application operation. A series of operations for moving a cursor and pressing a return key are represented in text form and registered in the dictionary 13 to enable key operations corresponding to the contents, so that the computer device 2 can be operated with voice.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a speech processing apparatus for recognizing speech and performing speech processing.

[0002]

2. Description of the Related Art In a conventional voice processing apparatus, a voice and a text representing an operation of a cursor, a key or the like are stored in association with each other, and processing is performed according to the stored text when an input voice is recognized. Was to run.

[0003]

As described above, there have conventionally been systems that can operate a personal computer by voice. However, in these systems, registration of operations is troublesome, and commands usable for each application are fixed. It was not easy to use.

[0004] Collection of inspection results of plants or equipment,
It is necessary to use a sound processing device for collecting the examination results of various measuring instruments, etc., and immediately take these results as data in a computer device (personal computer), and to save the labor to collect the results.

An object of the present invention is to provide a voice processing apparatus that meets such needs, contributes to labor saving, is easy to use by a worker using voice, and can immediately execute work contents. And

[0006]

SUMMARY OF THE INVENTION In order to solve this technical problem, the present invention allows a series of key operations on a computer device to be freely registered in a dictionary, so that the operation can be specified by voice or phrase. did. By doing so, all operations from starting the application to data input, data storage, and termination can be operated by voice commands.

More specifically, the present invention provides a voice input device for inputting a voice, a voice recognition device for recognizing the input voice, a reading storage means for storing a specified reading, and a reading and cursor, key and the like. Text storage means for storing text representing operations in association with each other; text file storage means for storing a series of texts that execute the contents of reading according to the text; and reading specified from the voice recognized by the voice recognition device. Executing means for recognizing and reading a series of texts from the text file storage means in response to the reading and executing the contents of the series of texts. .

[0008] The present invention provides a voice input device for inputting voice,
A voice recognition device for recognizing an input voice, a reading storage means for storing a specified reading, a text storage means for storing a reading and a text representing an operation of a cursor, a key or the like in association with each other; Text file storage means for storing a series of texts to be executed in accordance with the text, and contents of the application operation from start to reading, data input, data storage, and termination to the text stored in the text storage means and text file storage means And an execution means for executing the sound processing based on the sound processing.

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment according to the present invention will be described below with reference to the drawings.

In FIG. 1, the speech processing device comprises a speech recognition device 1 and a computer device (personal computer) 2.

The voice recognition device 1 includes an A / D conversion unit 4 for A / D converting a voice command input from an external microphone 3, a voice recognition unit 5 for recognizing the converted signal as voice, and a voice recognition unit 5. And a processing unit (CPU) 9 for exchanging voice data. This speech dictionary functions as a storage unit, and stores the reading 7 and the index 8 corresponding thereto. This index is transmitted to the computer device 2 via the communication circuit 10.

The computer device 2 includes an arithmetic processing unit (C
PU) 11, an application operation unit 12 that operates upon receiving a command, and a voice dictionary (PC side) 13 for exchanging data with these. This speech dictionary functions as a storage unit, and stores the text 14 and the index 1
5 is stored. This index corresponds to the aforementioned index 8 transmitted via the communication circuit 10.

Accordingly, these two voice dictionaries have a relationship between reading, text and index, as shown in a correspondence section 16 indicating the correspondence between "reading" and "text".
The speech recognition device-side speech dictionary 6 stores readings and indexes, and the computer device-side speech dictionary 13 has corresponding texts and indexes as dictionaries. The speech recognition device 1 sends the index value of the recognized word to the computer device 2, and the computer device 2 causes the application operation unit 12 to execute the key operation indicated by the index in the application operation.

A series of operations such as moving a cursor and pressing an enter key are expressed in the above-described text, and by registering them in a dictionary, key operations and the like corresponding to the contents can be performed on a personal computer. did.

The text will be described in more detail as follows. The structure of a text file consisting of text and a series of texts to be executed according to the text is as follows.

Reading text, text file [DOWN] Cursor [PGUP] Scroller [ENTER] Return [UP2] [RIGHT] Cursor double [CTRL] [ESC] rcalc.exe, like this By doing so, the operation of the personal computer can be registered in the voice dictionary in advance, so that the personal computer can be operated by voice.

To explain the symbols here, basically, each key of the personal computer can be a text. The text corresponding to the target key can be set freely. An example of the text and target key is shown below.

Key for text ＾: CTRL [ENTER]: ENTER [DOWN]: ↓ [UP]: ↑ [RIGHT]: → [LEFT]: ← Next, an example of editing with a text file is shown.

[UP], cursor up [UP2], cursor up [UP3], cursor up [DOWN], cursor up [DOWN2], cursor up [DOWN3], cursor up [RIGHT], cursor up [RIGHT2], cursor two [RIGHT3], cursor three [LEFT], cursor left [LEFT2], cursor two [LEFT3], cursor three [PGUP], scroll up [PGDN], scroll [ [BS2], two [BS3], three [ENTER], return [ENTER] [RIGHT] [UP], 〔[ENTER], ＾ [HOME] [DOWN4] [ RIGHT], [HOME] [DOWN4] [RIGHT8], Health [HOME], Gyo no Sento [HOME], Health [TAB], Tab [INSERT], Insert [DEL], Delete ＾ (o), Open a file ＾ (n), き (p), ＾ (s), ほ (c), copy ＾ (v), crucifix ＾ (x), cut と り (z), Return ＾ (y), repeat ＾ (f), kensaku ＾ (h), chikan [F1], help's display [F2], change [UP] ＾ [INSERT] [DOWN] [ENTER
R] [RIGHT], same as above [F4], application Y, yes N, no [ESC], cancel% [F], menu file% [E], menu change% [V] , Menu information% [I], menu information% [O], menu information% [T], menu tool% [W], menu window% [H], menu help ＾ [F9] , い し ょ う Ｆ [F10], い か さ [F5], original size ＾ [F4], close the file! Enter! NEXT, epilepsy! Before, before! AFTER, next! CANCEL, take it! IMEON, Japanese mode! IMEOFF, Japanese mode ＾ [ESC] rnotepad.exe, memo じ [ESC] rcalc, exc,, た ＾ [ESC] rc: \ msoffice \ excel \ excel.exe, じ セ ル[ESC] rc: \ TK \ TK. BAT, balance て (g) Helium [ENTER] [END] [DOWN
2), HELIUM ＾ (g) argon [ENTER] [END] [DOWN
ARGUON II (g) Various flow rates [ENTER] [END] [DOWN]
2], KAKUSYURYUYO ＾ (g) H2 series [ENTER] [END] [DOWN
2], ETSU-KEI H2KEI (g) N2 series [ENTER] [END] [DOWN
2], Entsu-kei N2KEI (g) Mixing flow rate [ENTER] [END] [DOWN]
2) 、 Kongoryuyo ＾ (g) Mixed gas system [ENTER] [END] [DOW
N2], KONGOGASUKEI ＾ (g) H2 analysis [ENTER] [END] [DOWN
2), H2BUNSEKI ＾ (g) Various articles [ENTER] [DOWN], KAKUSYUKIJI ＾ (g) Mixed articles [ENTER] [DOWN], KONGOKIJI% [TAB] , Application change # 1, onset # 2, onset # 3, onset # 4, onset ＾ [PGUP], previous sheet ＾ [PGDN], next sheet [ BS], return [DEL], rewrite In this way, you can easily edit and register your favorite key operations with a free utterance, and also with a text file. The audio processing device can be easily formed without any modification.

In connection with the application operation instruction, a text file reading example 1 {[HOME] [DOWN}] [RIGHT] HISHI In the case of reading "HISHI", how it functions is shown in FIG.
It will be described based on.

When moving to the date input area (B) at the position of the input area (A), "his" is uttered. The execution is automatically performed according to the text registered by the voice command, and moves to the date area (B). This makes it possible to input a date in the date area (B). ＾ [HOME], [DOWN4], [RIGHT]
Is described as follows.

Key operation applicable (a)） [HOME] = CTRL + HOME key pressed (b) [DOWN4] = ↓ key pressed four times (c) [RIGHT] = → key pressed once It can be understood that the same applies to "@ [HOME] [DOWN4] [RIGHT]".

Example 2 ＾ (g) helium [ENTER]
[END] [DOWN2], how to function in the case of the reading "Herimukyokyusetsu" will be described with reference to FIG.

When the user wants to move to the input area (BB) of the input range "helium" at the position of the input area (AA) of the input range (A), he utters "Helium". The execution is automatically performed according to the text registered by the voice command, the input range is switched, and the input area moves to (BB). That is, (d) the function of switching the input range from (A) to helium (e) the function of moving to the input area (BB) is executed. This makes it possible to input the state of "helium" of the plant to the computer device in the input area (BB).

(G) Helium [ENTER] represents text, and [END] [DOWN2] represents reading. The state corresponding to the key operation is as follows.

Key operation applicable ＾ (g) = CTRL + G key pressed Helium [ENTER] = key input of “helium” and then ENTER key pressed [END] = END key pressed [DOWN2] = ↓ key pressed twice As described above, “＾ (g) Argon [ENTER] [EN
D] [DOWN2], and certain functions are also used. These functions are the same and can be easily understood.

[0027]

As described above, according to the present invention, the user can easily edit and register any key operation and cursor operation with a free voice command (reading) by using a text file. Audio processing can be performed without creating. As a result, it is possible to execute the contents of the application operation up to start-up, data input, data storage, and termination by a voice command.

[Brief description of the drawings]

FIG. 1 is a block diagram for explaining an embodiment of the present invention.

FIG. 2 is a functional diagram showing the functions of the present invention.

FIG. 3 is a functional diagram showing the functions of the present invention.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Speech recognition apparatus, 2 ... Computer apparatus, 5 ... Speech recognition part, 6 ... Speech dictionary part (device side), 7 ... Reading, 8 ... Index, 9 ... CPU, 10 ... Communication circuit, 11 ... CP
U, 12: application operation unit, 13: voice dictionary (PC side), 14: text, 15: index, 16: corresponding unit.

Claims (2)

[Claims] A voice input device for inputting voice, a voice recognition device for recognizing the input voice, a reading storage means for storing a specified reading, and a text representing a reading and an operation of a cursor, a key or the like. Text storage means for storing in association with each other, text file storage means for storing a series of texts for executing the contents of reading according to the text, and recognizing a specified reading from the voice recognized by the speech recognition device, And an execution unit for executing a series of text contents by obtaining an execution procedure of the series of texts from the text file storage unit. 2. A voice input device for inputting voice, a voice recognition device for recognizing the input voice, a reading storage means for storing a specified reading, and a text representing a reading and an operation of a cursor, a key or the like. Text storage means for storing corresponding texts, text file storage means for storing a series of texts for executing the contents of reading according to the texts, and contents of application operations up to activation, data input, data storage, and termination in the readings. An audio processing device comprising: a text storage unit; and an execution unit that executes based on text stored in a text file storage unit.