JPH04184397A - Voice controller - Google Patents
Voice controllerInfo
- Publication number
- JPH04184397A JPH04184397A JP2313546A JP31354690A JPH04184397A JP H04184397 A JPH04184397 A JP H04184397A JP 2313546 A JP2313546 A JP 2313546A JP 31354690 A JP31354690 A JP 31354690A JP H04184397 A JPH04184397 A JP H04184397A
- Authority
- JP
- Japan
- Prior art keywords
- word
- section
- control
- controlled variable
- memory
- 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.)
- Granted
Links
- 241000282414 Homo sapiens Species 0.000 abstract description 5
- 230000035807 sensation Effects 0.000 abstract 2
- 238000006243 chemical reaction Methods 0.000 abstract 1
- 241000282412 Homo Species 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
Abstract
Description
【発明の詳細な説明】
産業上の利用分野
本発明は、音声入力による機器操作を人間同士の対話に
近い形態で実現する音声制御装置に関するものである。DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention relates to a voice control device that realizes device operation by voice input in a form similar to human interaction.
従来の技術
機械技術や電気技術等の発達により、我々のまわりには
さまざまな機器が存在している。それらの機器には、ダ
イヤル式、レバー式、ボタン式などによる何らかの調整
操作機能か付いているものが多い。人間がこれらの調整
を行うときには、その優れた感覚で数回の試行の後に最
適な値に調整を行うことができる。Conventional Technology Due to the development of mechanical technology, electrical technology, etc., various devices exist around us. Many of these devices have some type of adjustment function, such as a dial type, lever type, or button type. When humans make these adjustments, they can adjust to the optimal value after several trials using their excellent sense.
一方、音声認識技術は現在発展途上にある技術で、まだ
完成した技術であるとは言えないが、方式、用途によっ
ては実用されるものも出てきておりJ各種の機器に音声
認識技術が取り入れられるようになってきている。On the other hand, voice recognition technology is currently in the process of development and cannot be said to be a completed technology yet, but some methods and applications are beginning to be put into practical use, and voice recognition technology is being incorporated into various devices. It is becoming more and more common.
従来、音声認識技術を用いて何らかの機械を操作す木と
き、多くの場合は、人間が言葉を発声しそれを機械側が
認識し、その結果によって機器の操作を行っていた。し
かし、調整操作などの続けて何度も繰り返す操作につい
ては、同じ単語を何度も発声する必要が生じ、煩わしさ
を感じることになりかねない。Conventionally, when using voice recognition technology to operate some type of machine, in most cases a human utters words, the machine recognizes the words, and then operates the machine based on the results. However, when operations such as adjustment operations are repeated many times in succession, it becomes necessary to utter the same words over and over again, which can be bothersome.
一方、人間同士の対話では、話の流れをお互いに把握し
ているため、例えば「もう少し」とか「逆にコなどのよ
うに、先の会話にあった形容詞等を修飾する副詞だけで
話が通じることもある。On the other hand, in dialogue between humans, because both parties understand the flow of the conversation, they can use only adverbs that modify adjectives that were used in the previous conversation, such as "a little more" or "on the contrary, ko." Sometimes it works.
発明か解決しようとする課題
しかしながら、機械に対しては上述したような融通が効
かないため人間と対話するようにはいかず、普段人間同
士で話すときとの違和感から、使い勝手などの面で非常
に不自然さを感じ、音声認識による調整操作等はかえっ
て煩わしさを感じることになる。However, since machines do not have the flexibility mentioned above, they are not able to interact with humans, and because they feel uncomfortable when talking with humans, they are very difficult to use in terms of usability. It feels unnatural, and adjustment operations based on voice recognition are even more bothersome.
本発明は、上記のような従来の課題を解決するためのも
ので、音声入力で調整操作などの続けて何度も繰り返す
操作を行う場合に、人間同士で対話をしているような感
覚で機械を制御することのできる音声制御装置を提供す
ることを目的とする。The present invention is intended to solve the above-mentioned conventional problems, and when performing operations that are repeated many times in a row, such as adjustment operations, using voice input, it is possible to create a system that feels like a conversation between humans. The purpose of the present invention is to provide a voice control device that can control a machine.
課題を解決するための手段
この目的を達成するために、本発明は、音声入力を認識
する音声認識部と、音声認識部で認識した結果を語意に
より2つ以上に分類する語意分類部と、語意分類部によ
る分類結果によって制御量を設定する制御量設定部と、
直前に行った制御量設定部の制御量を記憶しておくメモ
リを設け、制御量設定部か、音声認識部による認識結果
と語意分類部による分類結果とメモリに記憶された制御
量の内の少なくとも2つによって制御量を決定する構成
を有している。Means for Solving the Problems In order to achieve this object, the present invention comprises: a speech recognition section that recognizes speech input; a word meaning classification section that classifies the results recognized by the speech recognition section into two or more types according to the meaning of the word; a control amount setting unit that sets a control amount based on the classification result by the word meaning classification unit;
A memory is provided to store the control amount of the control amount setting section that was performed immediately before, and the control amount setting section, the recognition result by the speech recognition section, the classification result by the meaning classification section, and the control amount stored in the memory are It has a configuration in which the control amount is determined by at least two factors.
作用
本発明は、上記構成により、直前に制御した量をメモリ
に記憶しておくことで、前の会話に現れた形容詞を修飾
するそれ自体では意味を持たない副詞を次に音声入力し
ても、その副詞に意味を持たせることが可能になり、よ
り人間同士の対話に近い感覚で制御操作が可能な音声制
御装置を実現することができる。Effect of the present invention With the above configuration, the amount controlled immediately before is stored in the memory, so that even if an adverb that modifies an adjective that appeared in the previous conversation and has no meaning by itself is input by voice next time, the amount controlled immediately before is stored in the memory. , it becomes possible to give meaning to the adverb, and it is possible to realize a voice control device that allows control operations to be performed with a feeling closer to human interaction.
実施例
以下、本発明の一実施例について図面を参照しながら説
明する。図は本発明の一実施例における音声制御装置の
ブロック結線図である。EXAMPLE Hereinafter, an example of the present invention will be described with reference to the drawings. The figure is a block diagram of a voice control device according to an embodiment of the present invention.
図において、1は音声を入力するマイクロホン、2は音
声の認識を行う音声認識部、3は音声認識部2において
認識された単語を基本語と補助語に分類を行う語意分類
部、4は音声認識部2において認識された単語が基本語
のときに制御量を決定する第1制御量設定部、5は音声
認識部2において認識された単語が補助語のときに制御
量を決定する第2制御量設定部、6は前回行った第1制
御量設定部4または第2制御量設定部5の制御量を記憶
しておくためのメモリ、7は第1制御量設定部4または
第2制御量設定部5で決定した制御量により被制御機器
8をコントロールする制御部である。In the figure, 1 is a microphone that inputs speech, 2 is a speech recognition unit that recognizes speech, 3 is a word meaning classification unit that classifies words recognized by speech recognition unit 2 into basic words and auxiliary words, and 4 is speech A first control amount setting section 5 determines the control amount when the word recognized in the recognition section 2 is a basic word, and a second control amount setting section 5 determines the control amount when the word recognized in the speech recognition section 2 is an auxiliary word. A controlled variable setting section, 6 is a memory for storing the previously performed controlled variable of the first controlled variable setting section 4 or the second controlled variable setting section 5, and 7 is the first controlled variable setting section 4 or the second control This is a control unit that controls the controlled device 8 based on the control amount determined by the amount setting unit 5.
以上のように構成された音声制御装置について、被制御
機器8がボリュームであり、このボリュームの大小を調
節する操作を例として、以下その動作を説明する。The operation of the audio control device configured as described above will be described below, with the controlled device 8 being a volume, taking as an example an operation to adjust the volume.
まず、いくつかの予め設定しておく事柄がある音声認識
部2には、音声認識に使用する単語を登録しておく。語
意分類部3には、音声認識部2に登録した単語が基本語
か補助語のとちらに属する単語であるかの情報を設定し
ておく。基本語は相反する意味を持つ2単語もしくはそ
れに同義語を加えたものであり、補助語は前に発声した
単語に対する背定語・否定語、程度を表す言葉なとであ
る。第1制御量設定部4には、基本語の各単語ごとに制
御する量を、制御を行う前から後へ加算または減算する
値として登録しておく。第2制御量設定部5には、補助
語の各単語ごとに、直前に行った制御に対する制御後の
倍率として制御量を登録しておく。First, words to be used for speech recognition are registered in the speech recognition section 2, which has several preset settings. The word meaning classification section 3 is set with information indicating whether the word registered in the speech recognition section 2 belongs to a basic word or an auxiliary word. A basic word is two words with contradictory meanings or a synonym added to them, and an auxiliary word is a declarative or negative word for the previously uttered word, or a word that expresses degree. In the first control amount setting section 4, the amount to be controlled for each basic word is registered as a value to be added or subtracted from before to after control. In the second control amount setting unit 5, a control amount is registered for each word of the auxiliary word as a multiplication factor after the control performed immediately before.
ボリュームの調節操作の例としては、「大きく」、「小
さく」を基本語として、「もう少し」を補助語として登
録しておく。調整量は、「大きく」は+20、「小さく
」は−2,0、「もう少し」は+0,5を設定しておく
。As examples of volume adjustment operations, "louder" and "lower" are registered as basic words, and "a little more" is registered as an auxiliary word. The adjustment amount is set to +20 for "larger", -2.0 for "smaller", and +0.5 for "a little more".
マイクロホン1から単語音声が入力されると、音声認識
部2では音声認識を行い、その認識結果情報を単語とし
て語意分類部3に送る。語意分類部3では、認識結果情
報である単語が、基本語と補助語のどちらに属する単語
であるかを分類する。When word speech is input from the microphone 1, the speech recognition section 2 performs speech recognition and sends the recognition result information as a word to the meaning classification section 3. The word meaning classification unit 3 classifies whether the word, which is the recognition result information, belongs to a basic word or an auxiliary word.
基本語のときは、第1制御量設定部4に予め設定してお
いたその認識単語に対する値の分だけ制御を行う。また
、同時に、制御を行った量をメモリ6に記憶する。In the case of a basic word, control is performed by the value for the recognition word set in advance in the first control amount setting section 4. At the same time, the controlled amount is stored in the memory 6.
「太き(jか入力された場合は、ボリュームを現在の値
から設定した値、即ち÷20の分だけ「大きく」する操
作を行い、同時にこの制御した量である。+20をメモ
リに蓄える。If "thick" (j) is input, perform an operation to "increase" the volume from the current value by the set value, that is, ÷20, and at the same time store this controlled amount +20 in the memory.
認識結果か補助語のときは、語意分類部3から第2制御
量設定部5に単語か送られたときに、メモリ6内に蓄え
られている前回の制御量を呼び出し、その値に予め登録
しておいた値を掛は合わせて制御を行う。このときの制
御量もメモリ6に記憶する。例えば「もう少し」が入力
された場合、この単語の持つ制御量、即ち+05をメモ
リ6に蓄えられていた直前の制御量(ここでは+20)
に街は合わせ、+1.0の分だけボリュームを調節する
。また、同時にこの制御量+1.0をメモリ6に蓄える
。In the case of a recognition result or an auxiliary word, when the word is sent from the meaning classification section 3 to the second control amount setting section 5, the previous control amount stored in the memory 6 is called and registered in advance to that value. Control is performed by multiplying the values set in advance. The control amount at this time is also stored in the memory 6. For example, when "a little more" is input, the control amount of this word, that is +05, is changed to the previous control amount stored in the memory 6 (+20 in this case).
, and adjust the volume by +1.0. At the same time, this control amount +1.0 is stored in the memory 6.
制御部7は、第1制御量設定部4または第2制御量設定
部5から送られてきた制御量により被制御1lltlj
、器8(ここではボリューム)の制御を行う。The control unit 7 controls the controlled variable 1lltlj based on the controlled variable sent from the first controlled variable setting unit 4 or the second controlled variable setting unit 5.
, the device 8 (volume in this case).
なお、本実施例では音声認識部2における認識の対象を
単語としているが、これは文章なと単語以外でもよい。In this embodiment, the speech recognition unit 2 recognizes words, but it may be other than words, such as sentences.
発明の効果
以上のように本発明は、直前に制御した量をメモリに記
憶しておくことで、前の会話に現れた形容詞を修飾する
それ自体では意味を持たない副詞を次に音声入力しても
、その副詞に意味を持たせることか可能になる。従って
、機器を何度も続けて音声入力で制御する際に、人間同
士でやりとりしているかのように音声入力が行えるので
、音声制御装置に対する煩わしさを和らげることができ
、結果として、より人間同士の対話に近い感覚で制御操
作が可能な音声制御装置を実現することができる。Effects of the Invention As described above, the present invention stores in memory the amount controlled just before, and then inputs by voice an adverb that modifies an adjective that appeared in the previous conversation and has no meaning by itself. However, it becomes possible to give meaning to the adverb. Therefore, when controlling a device using voice input over and over again, voice input can be performed as if it were a human being communicating with another person, reducing the inconvenience of voice control devices and, as a result, making it more human-friendly. It is possible to realize a voice control device that allows control operations to be performed with a feeling similar to a conversation between two people.
図は本発明の一実施例における音声制御装置のブロック
結線図である。
1・・・マイクロホン、2・・・音声認識部、3・・・
語意分類部、4・・・第1制御量設定部、5・・・第2
制御量設定部、6・・・メモリ、7・・・制御部、8・
・・被制御機器。
代理人の氏名 弁理士 小蝦治 明 1iカ12名制砲
蓋決定手段The figure is a block diagram of a voice control device according to an embodiment of the present invention. 1...Microphone, 2...Speech recognition unit, 3...
word meaning classification section, 4... first control amount setting section, 5... second
Controlled amount setting section, 6... Memory, 7... Control section, 8.
...Controlled equipment. Name of agent Patent attorney Akira Koeji 1i car 12 person system
Claims (1)
識した結果を語意により2つ以上に分類する語意分類部
と、上記語意分類部による分類結果によって制御量を設
定する制御量設定部と、直前に行った上記制御量設定部
の制御量を記憶しておくメモリを有し、上記制御量設定
部が、上記音声認識部による認識結果と上記語意分類部
による分類結果と上記メモリに記憶された制御量の内の
少なくとも2つによって制御量を決定することを特徴と
する音声制御装置。a speech recognition section that recognizes speech input; a word meaning classification section that classifies the recognition result by the speech recognition section into two or more types according to word meaning; and a control amount setting section that sets a control amount based on the classification result by the word meaning classification section. , has a memory for storing the control amount of the control amount setting section that was performed immediately before, and the control amount setting section stores in the memory the recognition result by the speech recognition section and the classification result by the word meaning classification section. A voice control device characterized in that a control amount is determined based on at least two of the control amounts.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2313546A JP2830460B2 (en) | 1990-11-19 | 1990-11-19 | Voice control device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2313546A JP2830460B2 (en) | 1990-11-19 | 1990-11-19 | Voice control device |
Publications (2)
Publication Number | Publication Date |
---|---|
JPH04184397A true JPH04184397A (en) | 1992-07-01 |
JP2830460B2 JP2830460B2 (en) | 1998-12-02 |
Family
ID=18042626
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2313546A Expired - Fee Related JP2830460B2 (en) | 1990-11-19 | 1990-11-19 | Voice control device |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP2830460B2 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005345903A (en) * | 2004-06-04 | 2005-12-15 | Honda Motor Co Ltd | Vocal equipment control unit |
JP2008003474A (en) * | 2006-06-26 | 2008-01-10 | Funai Electric Co Ltd | Electronic apparatus |
JP2014134791A (en) * | 2012-12-31 | 2014-07-24 | Samsung Electronics Co Ltd | Display device and control method |
-
1990
- 1990-11-19 JP JP2313546A patent/JP2830460B2/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005345903A (en) * | 2004-06-04 | 2005-12-15 | Honda Motor Co Ltd | Vocal equipment control unit |
JP2008003474A (en) * | 2006-06-26 | 2008-01-10 | Funai Electric Co Ltd | Electronic apparatus |
JP2014134791A (en) * | 2012-12-31 | 2014-07-24 | Samsung Electronics Co Ltd | Display device and control method |
Also Published As
Publication number | Publication date |
---|---|
JP2830460B2 (en) | 1998-12-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6006187A (en) | Computer prosody user interface | |
EP0852051B1 (en) | Process for automatic control of one or more devices by voice commands or by real-time voice dialog and apparatus for carrying out this process | |
US6513011B1 (en) | Multi modal interactive system, method, and medium | |
JPH04201745A (en) | Power seat for automobile | |
JP4523257B2 (en) | Audio data processing method, program, and audio signal processing system | |
Matsusaka et al. | Conversation robot participating in group conversation | |
CN106992004A (en) | A kind of method and terminal for adjusting video | |
JP2018049132A (en) | Voice dialogue system and method for voice dialogue | |
CN109688271A (en) | The method, apparatus and terminal device of contact information input | |
JPH04184397A (en) | Voice controller | |
JPH08166866A (en) | Editing support system equipped with interactive interface | |
JP2001268669A (en) | Device and method for equipment control using mobile telephone terminal and recording medium | |
JPH06139044A (en) | Interface method and device | |
JP2008216735A (en) | Reception robot and method of adapting to conversation for reception robot | |
JPH04338817A (en) | Electronic equipment controller | |
Edwards | Redundancy and adaptability | |
JP2001188788A5 (en) | ||
JPH11175093A (en) | Method for recognizing/confirming/responding voice | |
Berg et al. | Adaptation in Speech Dialogues–Possibilities to Make Human-Computer-Interaction More Natural | |
CN112558753A (en) | Multimedia interaction mode switching method and device, terminal and storage medium | |
Kouroupetroglou et al. | 4.7 Speech Technology for Disabled and Elderly People | |
JPH02230225A (en) | Camera control system | |
JPH0283727A (en) | Voice interaction equipment | |
JP2020067584A (en) | Communication device and control program for communication device | |
JP2004151562A (en) | Method for controlling voice interaction and voice interaction control device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20080925 Year of fee payment: 10 |
|
LAPS | Cancellation because of no payment of annual fees |