JPH08328579A - Speach recognition device - Google Patents

Speach recognition device

Info

Publication number
JPH08328579A
JPH08328579A JP7136312A JP13631295A JPH08328579A JP H08328579 A JPH08328579 A JP H08328579A JP 7136312 A JP7136312 A JP 7136312A JP 13631295 A JP13631295 A JP 13631295A JP H08328579 A JPH08328579 A JP H08328579A
Authority
JP
Japan
Prior art keywords
voice
microphone
input
unit
speach
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
JP7136312A
Other languages
Japanese (ja)
Inventor
Emiko Haruta
江美子 治田
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.)
NEC Corp
Original Assignee
NEC Corp
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 NEC Corp filed Critical NEC Corp
Priority to JP7136312A priority Critical patent/JPH08328579A/en
Publication of JPH08328579A publication Critical patent/JPH08328579A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE: To provide a speach recognition device without causing enlargement and cost increase of the device itself according to the increase of the number of speach input means. CONSTITUTION: This device is constituted of microphones 1-1 to 1-n being plural speach input parts, a speach recognition part 3 for recognizing the speach inputted to the microphones 1-1 to 1-n, a microphone connection part 2 for connecting the microphones 1-1 to 1-n with the speach recognition part 3, a microphone selection part 4 for selecting the microphone by the recognition result in the speach recognition part 3 and a selected microphone information part 5 for informing an operator of the microphone selected by the microphone selection part 4.

Description

【発明の詳細な説明】Detailed Description of the Invention

【0001】[0001]

【産業上の利用分野】本発明は、音声認識装置に関し、
特に、複数の音声入力部からの音声入力を行う音声認識
装置に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice recognition device,
In particular, the present invention relates to a voice recognition device that inputs voices from a plurality of voice input units.

【0002】[0002]

【従来の技術】複数の音声入力手段(マイクロフォン
等)を有する従来の音声認識装置においては、各音声入
力手段より入力された音声の区間だけが切り出されると
同時に、各音声区間にその入力開始時間の早い方から、
またはその終了時間の早い方から優先順位が付けられ
て、各音声区間の音声データは各音声入力手段に対応し
た入力音声保存手段に一時保存される。その後、付加さ
れた順番に従って保存された音声データについての音声
認識が行われ、認識結果が出力されていた(例えば、特
開昭61−256397号公報参照)。
2. Description of the Related Art In a conventional voice recognition apparatus having a plurality of voice input means (microphones, etc.), only the section of the voice input by each voice input section is cut out, and at the same time, the input start time of each voice section is cut out. From the earliest
Alternatively, the voice data of each voice section is temporarily stored in the input voice storage means corresponding to each voice input means, with priorities being given from the earliest end time. After that, voice recognition is performed on the voice data stored according to the added order, and the recognition result is output (for example, see Japanese Patent Laid-Open No. 61-256397).

【0003】[0003]

【発明が解決しようとする課題】しかしながら上述した
従来の音声認識装置においては、複数の音声入力手段か
らの音声の入力を常時可能とするために、各音声入力手
段から入力された音声データを保存しておく入力音声保
存手段を音声入力手段の数分設けなければならない。そ
のため、音声入力手段の数が増加すると、それに伴って
装置そのものが大型化してしまったり、コストが高くな
ってしまう等の問題点がある。
However, in the above-mentioned conventional voice recognition device, the voice data input from each voice input means is stored so that the voice can be always input from the plurality of voice input means. It is necessary to provide as many input voice storage means as the number of voice input means. Therefore, when the number of voice input means is increased, the size of the device itself is increased and the cost is increased.

【0004】本発明は、上述したような従来の技術が有
する問題点に鑑みてなされたものであって、音声入力手
段の数が増加してもそれに伴う装置そのものの大型化や
コストアップが生ずることのない音声認識装置を提供す
ることを目的とする。
The present invention has been made in view of the above-mentioned problems of the prior art, and even if the number of voice input means is increased, the size of the apparatus itself and the cost are increased accordingly. An object of the present invention is to provide a speech recognition device that does not have such a problem.

【0005】[0005]

【課題を解決するための手段】上記目的を達成するため
に本発明は、複数の場所にそれぞれ設置される音声入力
部からの音声の入力を選択し、選択された音声の認識を
行う音声認識装置であって、前記音声入力部から音声が
入力された場合に、前記複数の音声入力部のうち音声が
入力された音声入力部を検出し、入力された音声の解析
及び認識を行い、認識結果を出力する音声認識部と、前
記各音声入力部と前記音声認識部との接続を行うマイク
ロフォン接続部と、前記音声認識部における解析及び検
出結果により前記マイクロフォン接続部における前記音
声入力部と前記音声認識部との接続状態を切り換えるこ
とによって前記音声入力部からの音声の入力の選択を行
うマイクロフォン選択部と、を有することを特徴とす
る。
In order to achieve the above object, the present invention selects a voice input from a voice input section installed in each of a plurality of places, and recognizes the selected voice. A device, when a voice is input from the voice input unit, detects the voice input unit to which the voice is input from the plurality of voice input units, analyzes and recognizes the input voice, and recognizes the voice. A voice recognition unit that outputs a result, a microphone connection unit that connects each of the voice input units and the voice recognition unit, and the voice input unit and the voice input unit in the microphone connection unit based on the analysis and detection results of the voice recognition unit. And a microphone selection unit for selecting a voice input from the voice input unit by switching a connection state with the voice recognition unit.

【0006】また、前記マイクロフォン選択部における
選択結果を出力する選択マイクロフォン通知部を有する
ことを特徴とする。
Further, it is characterized in that it has a selection microphone notifying section for outputting a selection result in the microphone selection section.

【0007】[0007]

【作用】上記のように構成された本発明では、音声入力
部から音声が入力されると、音声認識部に入力された音
声の情報によって、マイクロフォン選択部が、以後、音
声入力が可能となる音声入力部と、音声認識部との接続
を維持し、他の音声入力部と音声認識部との接続を断絶
させる。従って、その後、音声認識部と接続された音声
入力部から選択解除の旨の信号が入力されて、全ての音
声入力部と音声認識部との接続が復旧するまで、音声認
識部への音声の入力権は、選択された音声入力部によっ
て専有され、音声認識部に対する音声の入力が常時1つ
の音声入力部からに限られる。
According to the present invention configured as described above, when a voice is input from the voice input unit, the microphone selection unit can subsequently input a voice according to the voice information input to the voice recognition unit. The connection between the voice input unit and the voice recognition unit is maintained, and the connection between another voice input unit and the voice recognition unit is disconnected. Therefore, after that, a signal indicating the deselection is input from the voice input unit connected to the voice recognition unit, and until the connection between all the voice input units and the voice recognition unit is restored, the voice to the voice recognition unit The input right is occupied by the selected voice input unit, and the voice input to the voice recognition unit is always limited to one voice input unit.

【0008】[0008]

【実施例】以下に、本発明の実施例について図面を参照
して説明する。
Embodiments of the present invention will be described below with reference to the drawings.

【0009】図1は、本発明の一実施例の構成を示す図
である。
FIG. 1 is a diagram showing the configuration of an embodiment of the present invention.

【0010】本実施例は図1に示すように、複数の音声
入力部であるマイクロフォン1−1〜1−nと、マイク
ロフォン1−1〜1−nに入力された音声を認識するた
めの音声認識部3と、マイクロフォン1−1〜1−nと
音声認識部3との接続を行うマイクロフォン接続部2
と、音声認識部3における認識結果によりマイクロフォ
ンの選択を行うマイクロフォン選択部4と、マイクロフ
ォン選択部4において選択されたマイクロフォンをオペ
レータ(不図示)に通知する選択マイクロフォン通知部
5とから構成される。
In this embodiment, as shown in FIG. 1, microphones 1-1 to 1-n, which are a plurality of voice input units, and voices for recognizing voices input to the microphones 1-1 to 1-n. The recognition unit 3 and the microphone connection unit 2 for connecting the microphones 1-1 to 1-n and the voice recognition unit 3
And a microphone selection unit 4 that selects a microphone based on the recognition result of the voice recognition unit 3, and a selection microphone notification unit 5 that notifies an operator (not shown) of the microphone selected by the microphone selection unit 4.

【0011】以下に、上述した構成の本実施例の動作に
ついて説明する。
The operation of this embodiment having the above configuration will be described below.

【0012】初期状態として、全てのマイクロフォン1
−1〜1−nがマイクロフォン選択部4にて選択されて
おり、それにより、マイクロフォン接続部2において全
てのマイクロフォン1−1〜1−nが音声認識部3と接
続されている。
As an initial state, all microphones 1
All the microphones 1-1 to 1-n are connected to the voice recognition unit 3 in the microphone connection unit 2 because the microphone selection units 1 to 1-n are selected by the microphone selection unit 4.

【0013】マイクロフォン1−1から音声が入力され
ると、音声認識部3において、入力された音声が解析さ
れ、同時に、音声が入力されたマイクロフォンが検出さ
れ、入力された音声が、マイクロフォン選択の旨の音声
であると判断されると、マイクロフォンの検出結果がマ
イクロフォン選択部4に送られる。
When a voice is input from the microphone 1-1, the voice recognition unit 3 analyzes the input voice, and at the same time, the microphone into which the voice is input is detected, and the input voice is selected by the microphone. If it is determined that the voice is a voice to the effect, the detection result of the microphone is sent to the microphone selection unit 4.

【0014】マイクロフォン選択部4にマイクロフォン
の検出結果が送られると、マイクロフォン接続部2にお
ける音声認識部3との接続状態がマイクロフォン1−1
のみに切り換えられる。
When the microphone detection result is sent to the microphone selection unit 4, the connection state of the microphone connection unit 2 with the voice recognition unit 3 is changed to the microphone 1-1.
Can only be switched to.

【0015】また、同時に、選択マイクロフォン通知部
5に、マイクロフォン1−1のみが音声認識部3と接続
されている旨の信号が送られ、選択マイクロフォン通知
部5により、複数のマイクロフォン1−1〜1−nのう
ちマイクロフォン1−1のみが、現在、音声認識部3に
接続されていることがオペレータに通知される。
At the same time, a signal indicating that only the microphone 1-1 is connected to the voice recognition unit 3 is sent to the selected microphone notification unit 5, and the selected microphone notification unit 5 causes the plurality of microphones 1-1 to 1-1. The operator is notified that only the microphone 1-1 of 1-n is currently connected to the voice recognition unit 3.

【0016】ここで、1つのマイクロフォンが選択され
ている状態においては、他のマイクロフォンからの音声
の入力はできない。
Here, when one microphone is selected, voice cannot be input from other microphones.

【0017】そして、マイクロフォン1−1から音声認
識部3に対し、音声の入力が行われ、音声認識部3から
入力された音声の認識結果が出力される。
Then, a voice is input from the microphone 1-1 to the voice recognition unit 3, and the recognition result of the voice input from the voice recognition unit 3 is output.

【0018】マイクロフォン1−1からの一通りの音声
入力が終了すると、オペレータによりマイクロフォン1
−1を介してマイクロフォン選択解除の旨の音声が入力
される。
Upon completion of one type of voice input from the microphone 1-1, the operator operates the microphone 1
A voice indicating that the microphone selection is canceled is input via -1.

【0019】すると、マイクロフォン選択時と同様に、
マイクロフォン選択部4にマイクロフォン選択解除の旨
の信号が送られる。
Then, as in the case of selecting the microphone,
A signal to the effect that microphone selection is canceled is sent to the microphone selection unit 4.

【0020】マイクロフォン選択部4にマイクロフォン
選択解除の旨の信号が送られると、マイクロフォン選択
部4により、マイクロフォン選択部2における音声認識
部3とマイクロフォン1−1〜1−nとの接続状態が切
り換えられて全てのマイクロフォン1−1〜1−nが選
択され、音声認識部3と接続される。
When a signal for deselecting the microphone is sent to the microphone selection unit 4, the microphone selection unit 4 switches the connection state between the voice recognition unit 3 and the microphones 1-1 to 1-n in the microphone selection unit 2. Then, all the microphones 1-1 to 1-n are selected and connected to the voice recognition unit 3.

【0021】全てのマイクロフォン1−1〜1−nが音
声認識部3と接続されると、選択マイクロフォン通知部
5により、全てのマイクロフォン1−1〜1−nが選択
され、音声認識部3に接続されていることがオペレータ
に通知される。
When all the microphones 1-1 to 1-n are connected to the voice recognition unit 3, all the microphones 1-1 to 1-n are selected by the selection microphone notification unit 5, and the voice recognition unit 3 is selected. The operator is notified that the connection is established.

【0022】全てのマイクロフォン1−1〜1−nが選
択されている状態においては、全てのマイクロフォン1
−1〜1−nから音声の入力が可能となる。
When all the microphones 1-1 to 1-n are selected, all the microphones 1
It is possible to input voice from -1 to 1-n.

【0023】[0023]

【発明の効果】本発明は、以上説明したように構成され
ているので以下に記載するような効果を奏する。
Since the present invention is constructed as described above, it has the following effects.

【0024】請求項1に記載のものにおいては、音声入
力部から音声が入力されると、音声認識部に入力された
音声の情報によって、マイクロフォン選択部が、以後、
音声入力が可能となる音声入力部と、音声認識部との接
続を維持し、他の音声入力部と音声認識部との接続を断
絶する構成としたため、複数の音声入力部を有する音声
認識装置においても、音声認識部に対する音声の入力が
常時1つの音声入力部からに限られる。それにより、音
声入力部の数が増加しても、それに伴う装置そのものの
大型化やコストアップの発生を防止することができる。
According to the first aspect of the present invention, when a voice is input from the voice input unit, the microphone selection unit is activated by the voice information input to the voice recognition unit.
A voice recognition device having a plurality of voice input units, because the voice input unit capable of voice input and the voice recognition unit are connected and the connection between other voice input units and the voice recognition unit is disconnected. Also in the above, the voice input to the voice recognition unit is always limited to one voice input unit. As a result, even if the number of voice input units is increased, it is possible to prevent the device itself from increasing in size and increasing in cost.

【0025】請求項2に記載のものにおいては、マイク
ロフォン選択部における選択結果を出力する選択マイク
ロフォン通知部を設けたため、オペレータが音声を入力
しようとする場合、入力が可能かどうか容易に判断する
ことができる。
According to the second aspect of the present invention, since the selection microphone notification section for outputting the selection result in the microphone selection section is provided, when the operator tries to input a voice, it is possible to easily judge whether or not the input is possible. You can

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

【図1】本発明の一実施例の構成を示す図である。FIG. 1 is a diagram showing a configuration of an exemplary embodiment of the present invention.

【符号の説明】[Explanation of symbols]

1−1〜1−n マイクロフォン 2 マイクロフォン接続部 3 音声認識部 4 マイクロフォン選択部 5 選択マイクロフォン通知部 1-1 to 1-n Microphone 2 Microphone connection section 3 Speech recognition section 4 Microphone selection section 5 Selection microphone notification section

Claims (2)

【特許請求の範囲】[Claims] 【請求項1】 複数の場所にそれぞれ設置される音声入
力部からの音声の入力を選択し、選択された音声の認識
を行う音声認識装置であって、 前記音声入力部から音声が入力された場合に、前記複数
の音声入力部のうち音声が入力された音声入力部を検出
し、入力された音声の解析及び認識を行い、認識結果を
出力する音声認識部と、 前記各音声入力部と前記音声認識部との接続を行うマイ
クロフォン接続部と、 前記音声認識部における解析及び検出結果により前記マ
イクロフォン接続部における前記音声入力部と前記音声
認識部との接続状態を切り換えることによって前記音声
入力部からの音声の入力の選択を行うマイクロフォン選
択部と、を有することを特徴とする音声認識装置。
1. A voice recognition device for selecting a voice input from a voice input section installed in each of a plurality of places and recognizing the selected voice, wherein the voice is input from the voice input section. In this case, a voice recognition unit that detects a voice input unit in which voice is input from the plurality of voice input units, analyzes and recognizes the input voice, and outputs a recognition result; and the voice input units. A microphone connection unit for connecting to the voice recognition unit; and the voice input unit by switching the connection state between the voice input unit and the voice recognition unit in the microphone connection unit according to the analysis and detection results of the voice recognition unit. A voice recognition device, comprising: a microphone selection unit that selects a voice input from the.
【請求項2】 請求項1に記載の音声認識装置におい
て、 前記マイクロフォン選択部における選択結果を出力する
選択マイクロフォン通知部を有することを特徴とする音
声認識装置。
2. The voice recognition device according to claim 1, further comprising a selection microphone notification unit that outputs a selection result in the microphone selection unit.
JP7136312A 1995-06-02 1995-06-02 Speach recognition device Pending JPH08328579A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP7136312A JPH08328579A (en) 1995-06-02 1995-06-02 Speach recognition device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP7136312A JPH08328579A (en) 1995-06-02 1995-06-02 Speach recognition device

Publications (1)

Publication Number Publication Date
JPH08328579A true JPH08328579A (en) 1996-12-13

Family

ID=15172264

Family Applications (1)

Application Number Title Priority Date Filing Date
JP7136312A Pending JPH08328579A (en) 1995-06-02 1995-06-02 Speach recognition device

Country Status (1)

Country Link
JP (1) JPH08328579A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1081682A2 (en) * 1999-08-31 2001-03-07 Pioneer Corporation Method and system for microphone array input type speech recognition
DE102014207437B4 (en) 2013-05-13 2019-12-05 Gm Global Technology Operations, Llc Speech recognition with a plurality of microphones

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH01216398A (en) * 1988-02-25 1989-08-30 Toshiba Corp Speech recognizing system

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH01216398A (en) * 1988-02-25 1989-08-30 Toshiba Corp Speech recognizing system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1081682A2 (en) * 1999-08-31 2001-03-07 Pioneer Corporation Method and system for microphone array input type speech recognition
EP1081682A3 (en) * 1999-08-31 2001-08-01 Pioneer Corporation Method and system for microphone array input type speech recognition
US7016836B1 (en) * 1999-08-31 2006-03-21 Pioneer Corporation Control using multiple speech receptors in an in-vehicle speech recognition system
DE102014207437B4 (en) 2013-05-13 2019-12-05 Gm Global Technology Operations, Llc Speech recognition with a plurality of microphones

Similar Documents

Publication Publication Date Title
US8701003B2 (en) Methods and apparatus for controlling a user interface based on the emotional state of a user
JP4679254B2 (en) Dialog system, dialog method, and computer program
US7844454B2 (en) Apparatus and method for providing voice recognition for multiple speakers
US6542868B1 (en) Audio notification management system
JP4346571B2 (en) Speech recognition system, speech recognition method, and computer program
US8606574B2 (en) Speech recognition processing system and speech recognition processing method
JP2004054080A (en) Method and device for data input
CN107329843A (en) Application program sound control method, device, equipment and storage medium
US20060095267A1 (en) Dialogue system, dialogue method, and recording medium
CN109979437A (en) Audio recognition method, device, equipment and storage medium
CN112735411A (en) Control method, client, vehicle, voice system, and storage medium
JP2008033198A (en) Voice interaction system, voice interaction method, voice input device and program
CN105791542B (en) Find the method, apparatus and mobile terminal of mobile terminal
JPH08328579A (en) Speach recognition device
CN110065502A (en) Vehicle and its control method and device
CN113438130A (en) Overtime monitoring method and device based on micro-service
KR20160047822A (en) Method and apparatus of defining a type of speaker
CN106055472A (en) Method, device and terminal equipment for entering debugging mode
TWI779237B (en) Automatic call distribution system and automatic call distribution method
JP2008005102A (en) Speech apparatus and system for speech communication
US20220095039A1 (en) Headphone, acoustic signal processing method, and program
JP2000066698A (en) Sound recognizer
JP2004354760A (en) Speech recognition device
JP6294863B2 (en) Output control device, output control system, output control method, and program
JP2005318101A (en) Telephone answering diagnostic device and telephone answering evaluating program