JPS6073729A - Speech processor - Google Patents

Speech processor

Info

Publication number
JPS6073729A
JPS6073729A JP58181444A JP18144483A JPS6073729A JP S6073729 A JPS6073729 A JP S6073729A JP 58181444 A JP58181444 A JP 58181444A JP 18144483 A JP18144483 A JP 18144483A JP S6073729 A JPS6073729 A JP S6073729A
Authority
JP
Japan
Prior art keywords
voice
signal
speech
recognizing
vru
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP58181444A
Other languages
Japanese (ja)
Inventor
Yutaka Mizoguchi
豊 溝口
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujitsu Ltd
Original Assignee
Fujitsu Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP58181444A priority Critical patent/JPS6073729A/en
Publication of JPS6073729A publication Critical patent/JPS6073729A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE:To surely perform prescribed speech processing without recognizing unnecessary voice from a loudspeaker, by providing a control device which makes a speech recognizing unit operate in a time relation which is opposite to the operation of a voice outputting unit. CONSTITUTION:Programs which respectively control the operation of a voice outputting device VPU and a speech recognizing device VRU are contained in the same place as a program S-CP which controls the whole system and the voice outputting device VPU and the speech recognizing device VRU are operated by a control signal from each device. Under such a condition, it is controlled that a signal 213 is simultaneously generated with a signal 22 when the voice outputting device controlling program operates the voice outputting device, by using the signal 213 to pause the speech recognizing function and another signal 214 for restoring the speech recognizing function and giving a function which generates the operation pause command of the speech recognizing device to the speed recognizing device controlling program.

Description

【発明の詳細な説明】 (1)発明の技術分野 本発明は音声出カニニットと音声認識ユニットが不必要
に結合することを防止した音声処理装置に関する。
DETAILED DESCRIPTION OF THE INVENTION (1) Technical Field of the Invention The present invention relates to a voice processing device that prevents unnecessary coupling of a voice output unit and a voice recognition unit.

(2)従来技術と問題点 第1図は従来の音声処理装置のシステム系統図を示して
いる。音声出カニニットVPU、音声認識ユニソ)VR
Uの動作をそれぞれ制御するプログラムがシステム全体
を制御するプログラム5−CPと通常は同一場所に格納
され、その結果の出力により制御信号を発生する装置が
、便宜上音声比カニニット制御プログラムVPU−CP
、音声認識ユニッ、ト制御プログラムVRU−CPと記
した場所に在り、各装置からの制御信号によって音声出
カニニットv p u、音声認識ユニッI−VRUを動
作させる。スピーカSP1マイクロホンMICが各ユニ
ットに接続され、システム制御プログラム5−cpと記
す部分に存在する。中央処理装置は陰極線管・キーボー
ドCRT/K Bと記す制御卓からの指令で動作する。
(2) Prior Art and Problems FIG. 1 shows a system diagram of a conventional audio processing device. Voice output crabnit VPU, voice recognition Unison) VR
The programs that control the operations of U are usually stored in the same location as the program 5-CP that controls the entire system, and the device that generates control signals based on the output of the results is the voice ratio crab unit control program VPU-CP for convenience.
, voice recognition unit, and control program VRU-CP, and operate the voice output unit vpu and voice recognition unit I-VRU in response to control signals from each device. A speaker SP1 microphone MIC is connected to each unit and exists in a part of the system control program 5-cp. The central processing unit operates according to instructions from a control console designated as cathode ray tube/keyboard CRT/KB.

即ちシステム制御プログラム5−cpがキーボードKB
からの指令112により起動されると、音声認識ユニッ
ト制御プログラムVRU−CPを起動する信号19が発
生され、該プログラムVRU−CPは音声認識ユニッ)
VRUの動作を開始させる。マイクロホンMICからの
入力音声16は、音声認識ユニットvRUにおいて認識
され、出力信号1Bを生成する。音声認識ユニット制御
プログラムVRU−CPはシステム制御プログラム5−
cpに対し、信号110により通知し、次いで音声出方
ユニット制御プログラムVPU−CPが信号14により
起動され、音声出カニニットは信号12により動作を開
始する。
That is, the system control program 5-cp is the keyboard KB.
When activated by a command 112 from the voice recognition unit, a signal 19 is generated to activate the voice recognition unit control program VRU-CP, and the program VRU-CP is activated by the voice recognition unit).
Start the VRU operation. The input speech 16 from the microphone MIC is recognized in the speech recognition unit vRU and generates an output signal 1B. The voice recognition unit control program VRU-CP is the system control program 5-
CP is notified by signal 110, then the voice output unit control program VPU-CP is activated by signal 14, and the voice output unit starts operation by signal 12.

音声認識結果はスピーカspに対し信号11が伝送され
出力する。音声出カニニット制御プログラムVPU−C
PはVPUがらの音声出力の終了信号13を待って信号
15により前記音声出方の終了をシステム制御プログラ
ム5−cpに通知する。音声の出力中も音声認識ユニッ
トVRUは依然として動作中であるから、前記音声出方
中に認識した結果は信号110により、システム制御プ
ログラム5−CPが取込み、次の1処理に移る。したが
って音声出力を始めたときスピーカがらの出力が壁など
に反射して、マイクロホンM■cに到来したとき、マイ
クロホンMICは話者の音声と判断し忠実に認識を行う
から、スピーカspがらの音声出力が認識されることに
なる。音声認識装置では話者の入力が不完全であれば、
再入力を促すためのガイダンスを出力することがあり、
その出方が話者の音声の直前に認識ユニットに入力する
ことになり、スピーカからの出力とマイクロホンの入力
間が結合した形になり、再入力を促すためのガイダンス
を繰り返して発する場合もあった。従来の音声認識装置
ではそれを防止する手段が特に施されてなく、スピーカ
からの出力を極度に小とする程度であった。なお信号1
11は音声認識結果を陰極線管CRTに表示するため使
用する。
The voice recognition result is output as a signal 11 transmitted to the speaker sp. Voice output crab knit control program VPU-C
P waits for the end signal 13 of the audio output from the VPU and notifies the system control program 5-cp of the end of the audio output using the signal 15. Since the voice recognition unit VRU is still in operation even while the voice is being output, the system control program 5-CP takes in the recognition result during the voice output by the signal 110 and moves on to the next process. Therefore, when audio output starts and the output from the speaker reflects off a wall etc. and reaches the microphone Mc, the microphone MIC determines that it is the speaker's voice and faithfully recognizes it, so the sound from the speaker SP The output will be recognized. If the speaker's input is incomplete in the speech recognition device,
Guidance may be output to prompt you to re-enter the information.
The way it is output is input to the recognition unit immediately before the speaker's voice, and the output from the speaker and input from the microphone are combined, and guidance may be repeatedly emitted to prompt re-input. Ta. Conventional speech recognition devices do not have any particular measures to prevent this, and the output from the speaker is kept extremely low. Furthermore, signal 1
Reference numeral 11 is used to display the voice recognition results on a cathode ray tube CRT.

(3)発明の目的 本発明の目的は前述の欠点を改善し、比較的簡易な構成
で容易・確実にスピーカ・マイクロホン間の不必要な結
合を遮断できる音声認識処理装置を提供することにある
(3) Purpose of the Invention The purpose of the present invention is to improve the above-mentioned drawbacks and to provide a voice recognition processing device that can easily and reliably block unnecessary coupling between a speaker and a microphone with a relatively simple configuration. .

(4)発明の構成 前述の目的を達成するための本発明の構成は、マイクロ
ホンを使用して、音声認識ユニットに入力した音声を認
識し、音声出カニニットからスピーカにより出力する音
声処理装置において、音声認識ユニットの動作を音声出
カニニットの動作と相反する時間関係で行わせる制御装
置を具備することである。
(4) Structure of the Invention The structure of the present invention to achieve the above-mentioned object is a voice processing device that uses a microphone to recognize the voice input to the voice recognition unit and outputs it from the voice output unit through the speaker. The object of the present invention is to include a control device that causes the voice recognition unit to operate in a time relationship that is contradictory to the voice output unit.

(5)発明の実施例 第2図は本発明の一実施例を構成を示す図で、第1図と
同一符号は同様のものを示す。また信号を示す数字の最
上位桁が2となっているものは、第1図において最上位
桁が1となっている信号と対応している。信号213は
音声認識の機能を中断させるもの、信号214は音声認
識の機能を復帰させるためのものを示す。音声認識ユニ
ット制御プログラム中に音声認識ユニットの動作中断指
令を発することができるものを具備させ、音声出方ユニ
ット制御プログラムが音声出方ユニットを動作させると
き信号22と同時に信号213を発するように制御する
。また信号23が到来したとき、信号214により音声
認識ユニット制御プログラムが再開される。信号213
.214の代わりに信号24.25によりシステム制御
プログラム5−cpからの信号29に併せ載せても良い
。或いは音声出方ユニット制御プログラムが音声Lm 
A&ユニット制御プログラムによる制御信号を受け、出
力すべき音声が到来しても、中止したり、暫く待つこと
とする場合も考えられる。
(5) Embodiment of the Invention FIG. 2 is a diagram showing the configuration of an embodiment of the present invention, and the same reference numerals as in FIG. 1 indicate the same parts. Also, the numbers indicating signals whose most significant digit is 2 correspond to the signals whose most significant digit is 1 in FIG. A signal 213 is for interrupting the voice recognition function, and a signal 214 is for restoring the voice recognition function. The voice recognition unit control program is provided with a program capable of issuing a command to interrupt the operation of the voice recognition unit, and the voice output unit control program is controlled to generate the signal 213 at the same time as the signal 22 when operating the voice output unit. do. Also, when the signal 23 arrives, the speech recognition unit control program is restarted by the signal 214. signal 213
.. Instead of the signal 214, the signal 24.25 may be added to the signal 29 from the system control program 5-cp. Or the sound output unit control program is the sound Lm
In response to a control signal from the A&unit control program, even if the audio to be output arrives, it may be decided to cancel or wait for a while.

(6)発明の効果 このようにして本発明によると、音声処理装置において
音声認識装置が常時動作可とならないから、スピーカか
らの不要な音声を認識せず所定の音声処理が確実にでき
る効果を有する。
(6) Effects of the Invention As described above, according to the present invention, since the voice recognition device in the voice processing device is not always operational, it is possible to reliably carry out predetermined voice processing without recognizing unnecessary voices from the speakers. have

【図面の簡単な説明】[Brief explanation of drawings]

第1図は従来の音声処理装置の構成を示す図、第2図は
本発明の一実施例の構成を示す図である。 v p u−音声出力ユニット VRU・−音声認識ユニット S −CP−制御プログラム VPU−CP−音声出力ユニット制御プログラムVRU
−CP−音声認識ユニット制御プログラムsp−スピー
カ MIC−・−マイクロホン特許出願人 富士通株式
会社 代理人 弁理士 鈴木栄祐
FIG. 1 is a diagram showing the configuration of a conventional audio processing device, and FIG. 2 is a diagram showing the configuration of an embodiment of the present invention. v p u-Voice output unit VRU・-Voice recognition unit S-CP-Control program VPU-CP-Voice output unit control program VRU
-CP-Speech Recognition Unit Control Program sp-Speaker MIC--Microphone Patent Applicant Fujitsu Limited Agent Patent Attorney Eisuke Suzuki

Claims (1)

【特許請求の範囲】[Claims] マイクロホンを使用して、音声認識ユニットに入力した
音声を認識し、音声出カニニットからスピーカにより出
力する音声処理装置において、音声認識ユニットの動作
を音声出カニニットの動作と相反する時間関係で行わせ
る制御装置を具備することを特徴とする音声処理装置。
In a voice processing device that uses a microphone to recognize the voice input to the voice recognition unit and outputs it from the voice output unit through a speaker, control that causes the voice recognition unit to operate in a time relationship that is contradictory to the operation of the voice output unit. An audio processing device comprising:
JP58181444A 1983-09-29 1983-09-29 Speech processor Pending JPS6073729A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP58181444A JPS6073729A (en) 1983-09-29 1983-09-29 Speech processor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP58181444A JPS6073729A (en) 1983-09-29 1983-09-29 Speech processor

Publications (1)

Publication Number Publication Date
JPS6073729A true JPS6073729A (en) 1985-04-25

Family

ID=16100872

Family Applications (1)

Application Number Title Priority Date Filing Date
JP58181444A Pending JPS6073729A (en) 1983-09-29 1983-09-29 Speech processor

Country Status (1)

Country Link
JP (1) JPS6073729A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62299997A (en) * 1986-06-20 1987-12-26 松下電器産業株式会社 Interactive type voice input/output unit
JPS63121096A (en) * 1986-11-10 1988-05-25 松下電器産業株式会社 Interactive type voice input/output device

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS58113991A (en) * 1981-12-26 1983-07-07 富士通株式会社 Voice recognition control system

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS58113991A (en) * 1981-12-26 1983-07-07 富士通株式会社 Voice recognition control system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62299997A (en) * 1986-06-20 1987-12-26 松下電器産業株式会社 Interactive type voice input/output unit
JPH0756595B2 (en) * 1986-06-20 1995-06-14 松下電器産業株式会社 Interactive voice input / output device
JPS63121096A (en) * 1986-11-10 1988-05-25 松下電器産業株式会社 Interactive type voice input/output device

Similar Documents

Publication Publication Date Title
US5864815A (en) Method and system for displaying speech recognition status information in a visual notification area
JP4837917B2 (en) Device control based on voice
JPH06100959B2 (en) Voice interaction device
JPH11231896A (en) Speech startup system
JPH0831021B2 (en) Voice guidance output control method
JPS6073729A (en) Speech processor
JPH02131300A (en) Voice recognizing device
JPS62105198A (en) Voice output control system
JPS5914769B2 (en) audio equipment
JPS59153238A (en) Voice input/output system
JPH0210559Y2 (en)
JP2000047848A (en) Voice output controlling system
JP2019020475A (en) Voice recognition device and voice recognition method
JPH02103599A (en) Voice recognizing device
JP3023137B2 (en) Voice recognition control device
JP2002182691A (en) Controller for controlling sound emitting device
JPH04246696A (en) Voice recognition device
JPH03216697A (en) Electronic equipment
JPH03200298A (en) Voice controller
JPH07175566A (en) Bell and key click control system at work station
JPH0430614B2 (en)
JP3294286B2 (en) Speech recognition system
JPS6248855B2 (en)
JPS61225996A (en) Voice recognition device
JPS6239899A (en) Conversation voice understanding system