JP2007264328A - Bathroom apparatus and voice operation system used therefor - Google Patents

Bathroom apparatus and voice operation system used therefor Download PDF

Info

Publication number
JP2007264328A
JP2007264328A JP2006089560A JP2006089560A JP2007264328A JP 2007264328 A JP2007264328 A JP 2007264328A JP 2006089560 A JP2006089560 A JP 2006089560A JP 2006089560 A JP2006089560 A JP 2006089560A JP 2007264328 A JP2007264328 A JP 2007264328A
Authority
JP
Japan
Prior art keywords
bathroom
voice
unit
acoustic model
speaker
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
Application number
JP2006089560A
Other languages
Japanese (ja)
Other versions
JP4784366B2 (en
Inventor
Akira Baba
朗 馬場
Kiyotaka Takehara
清隆 竹原
Kenji Okuno
健治 奥野
Shinpei Hibiya
新平 日比谷
Kenji Nakakita
賢二 中北
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.)
Panasonic Electric Works Co Ltd
Original Assignee
Matsushita Electric Works 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 Matsushita Electric Works Ltd filed Critical Matsushita Electric Works Ltd
Priority to JP2006089560A priority Critical patent/JP4784366B2/en
Publication of JP2007264328A publication Critical patent/JP2007264328A/en
Application granted granted Critical
Publication of JP4784366B2 publication Critical patent/JP4784366B2/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Bathtubs, Showers, And Their Attachments (AREA)

Abstract

<P>PROBLEM TO BE SOLVED: To provide a bathroom apparatus which suppresses deterioration in the recognition rate of voice recognition due to the influence of echo sound, and to provide a voice operation system used therefor. <P>SOLUTION: The voice operation system B used for the bathroom apparatus A includes an operation state detecting unit 24, which detects operation states of a plurality of bathroom devices C installed in a bathroom; an area detecting unit 13 which detects an estimated position, where a bathroom device C in operation detected by the operation state detecting unit 24 is used as an area where a speaker is present; a sound model storage unit 14 which stores a plurality of sound models M1 to Mn wherein different echo states are assumed respectively; a sound model selecting unit 15 which selects a model, corresponding to the echo state of the area detected by the area detecting unit 13 out of the sound models M1 to Mn stored in the sound model storage unit 14; a voice recognizing unit 16 recognizing the contents of a voice detected by a microphone MC by using the selected sound model; and a voice operation unit 17 which operates the corresponding bathroom device C, based on the recognition result of the voice recognizing unit 16. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

本発明は、浴室装置及びそれに用いる音声操作装置に関するものである。   The present invention relates to a bathroom device and a voice operation device used therefor.

従来より、給湯器の給湯温度や浴槽に溜める湯の温度や量を設定したり、追い炊きや湯はりなどの操作を行うための給湯コントローラが浴室内に設置されている。   2. Description of the Related Art Conventionally, a hot water controller for setting the hot water temperature of a water heater or the temperature and amount of hot water stored in a bathtub, or performing operations such as additional cooking and hot water is installed in the bathroom.

また近年、快適な入浴を実現するために、浴槽内に気泡を含んだジェット噴流を発生させるジェット噴流設備や、浴室内の暖房、換気、浴室乾燥を行う換気暖房乾燥設備や、映像あるいは音楽などを視聴するための映像音響設備が浴室内に設置されており、これらの設備を操作するためのコントローラも浴室装置として設置されていた。そのため浴室内には給湯コントローラとは別に、ジェット噴流設備、換気暖房乾燥設備、映像音響設備などの浴室機器をそれぞれ制御するための複数のコントローラが設置されることになり、コントローラの数が増えて、広い設置スペースを必要とするという問題があった。またコントローラの数が増えると、それぞれのコントローラの使用方法を覚えなければならず、使用方法の習熟に時間を要し、また複数のコントローラを操作するため使い勝手が悪かった。   In recent years, in order to realize comfortable bathing, jet jet equipment that generates jets containing bubbles in the bathtub, ventilation heating and drying equipment that performs heating, ventilation, and bathroom drying in the bathtub, video or music, etc. Audio-visual equipment for viewing the TV is installed in the bathroom, and a controller for operating these equipment is also installed as a bathroom device. Therefore, in addition to the hot water controller in the bathroom, multiple controllers for controlling bathroom equipment such as jet jet equipment, ventilation heating and drying equipment, and audiovisual equipment will be installed, increasing the number of controllers. There was a problem of requiring a large installation space. Further, as the number of controllers increases, it is necessary to learn how to use each controller, and it takes time to learn how to use them, and it is difficult to use because it operates a plurality of controllers.

そこで、例えば特許文献１に示されるような音声認識装置を用い、各種の浴室機器を制御するために使用者が音声で命令を発すると、その音声を認識して、操作対象の浴室機器を操作するようにした浴室装置および音声操作装置が提案されている。
特開２００４−１１７７２４号公報（段落番号［００２５］〜［００３２］、及び、図１） Therefore, for example, when a user issues a voice command to control various bathroom devices using a voice recognition device as disclosed in Patent Document 1, the voice is recognized and the bathroom device to be operated is operated. There have been proposed bathroom devices and voice operation devices.
JP 2004-117724 A (paragraph numbers [0025] to [0032] and FIG. 1)

上述の浴室装置および音声操作装置は、浴室内の話者が発した音声を認識して制御対象の浴室機器を制御するのであるが、浴室は反射の強い環境であるため、音声が残響音の影響を受けて変形し、音声認識の認識率が低下するという問題があった。   The bathroom device and the voice operation device described above recognize the voice uttered by the speaker in the bathroom and control the bathroom device to be controlled. However, since the bathroom is a highly reflective environment, the voice is reverberant. There is a problem that the recognition rate of voice recognition is lowered due to deformation.

このような問題に対して、上述の特許文献１に示される音声認識装置では、音声認識に用いる音響モデルとして、残響時間の異なる複数の音響モデルを用意し、話者が入力した音声に対して最も類似度の高い音響モデルを用いて音声認識を行うようにしているが、浴室内で話者が移動すると、話者と話者の話す声を集音するマイクの位置が変化して反射特性が変化するため、音響モデルが一致しなくなる。したがって話者が移動した後に話した最初の音声は、音響モデルが正しく選択されていないため、認識率が低下してしまうという問題があった。また残響時間をもとに音響モデルを選択する場合に、音響モデルの選択を誤ると、音声認識の認識率が低下するという問題もあった。   For such a problem, the speech recognition apparatus disclosed in Patent Document 1 described above prepares a plurality of acoustic models having different reverberation times as acoustic models used for speech recognition, and for speech input by a speaker. Speech recognition is performed using the acoustic model with the highest similarity, but when the speaker moves in the bathroom, the position of the microphone that collects the voice of the speaker and the speaker changes and the reflection characteristics change. Changes, the acoustic models do not match. Therefore, the first speech spoken after the speaker has moved has a problem that the recognition rate decreases because the acoustic model is not correctly selected. In addition, when an acoustic model is selected based on the reverberation time, if the acoustic model is selected incorrectly, there is a problem that the recognition rate of speech recognition is lowered.

本発明は上記問題点に鑑みて為されたものであり、その目的とするところは、反響音の影響によって音声認識の認識率が低下するのを抑制した浴室装置及びそれに用いる音声操作装置を提供することにある。   The present invention has been made in view of the above problems, and an object of the present invention is to provide a bathroom device that suppresses a decrease in the recognition rate of speech recognition due to the influence of reverberant sound and a voice operation device used therefor. There is to do.

上記目的を達成するために、請求項１の発明は、浴室に設けられた複数の浴室機器と、浴室に設けられた音声検出部と、浴室内で話者がいる領域を検出する領域検出部と、異なる反響状態をそれぞれ想定した複数の音響モデルを記憶する音響モデル記憶部と、音響モデル記憶部に記憶された複数の音響モデルから、領域検出部による検出領域の反響状態に対応した音響モデルを選択する音響モデル選択部と、音響モデル選択部により選択された音響モデルを用いて音声検出部が検出した音声の内容を認識する音声認識部と、音声認識部により認識された音声の内容にしたがって対応する浴室機器を操作する音声操作部とを備えて成ることを特徴とする。   In order to achieve the above object, the invention of claim 1 includes a plurality of bathroom devices provided in a bathroom, a voice detection unit provided in the bathroom, and a region detection unit that detects a region where a speaker is present in the bathroom. And an acoustic model storage unit storing a plurality of acoustic models each assuming different echo states, and an acoustic model corresponding to the echo state of the detection region by the region detection unit from the plurality of acoustic models stored in the acoustic model storage unit An acoustic model selection unit that selects the speech model, a speech recognition unit that recognizes speech content detected by the speech detection unit using the acoustic model selected by the acoustic model selection unit, and a speech content recognized by the speech recognition unit Therefore, it is provided with the audio | voice operation part which operates corresponding bathroom equipment.

請求項２の発明は、請求項１の発明において、話者の顔が向いている方向を検出する方向検出部を設け、音響モデル選択部は、領域検出部による検出領域と、方向検出部による検出方向とをもとに、話者が発する声の残響状態に対応する音響モデルを選択することを特徴とする。   According to a second aspect of the present invention, in the first aspect of the invention, a direction detection unit that detects a direction in which the speaker's face is facing is provided, and the acoustic model selection unit includes a detection region by the region detection unit and a direction detection unit. An acoustic model corresponding to a reverberation state of a voice uttered by a speaker is selected based on a detection direction.

請求項３の発明は、請求項１又は２の発明において、各浴室機器の稼働状態を検出する稼働状態検出部を設け、領域検出部が、稼働状態検出部により検出された稼働中の浴室機器を使用する場合の予想位置を話者の居る領域として検出することを特徴とする。   Invention of Claim 3 provides the operation state detection part which detects the operation state of each bathroom apparatus in invention of Claim 1 or 2, and the area | region detection part is operating bathroom apparatus detected by the operation state detection part It is characterized in that an expected position when using the is detected as an area where a speaker is present.

請求項４の発明は、請求項１乃至３の何れか１項に記載の浴室装置に用いられる音声操作装置であって、音声検出部と、領域検出部と、音響モデル記憶部と、音響モデル選択部と、音声認識部と、音声操作部とを備えて成ることを特徴とする。   A fourth aspect of the present invention is a voice operation device used in the bathroom device according to any one of the first to third aspects, wherein the voice detection unit, the region detection unit, the acoustic model storage unit, and the acoustic model are provided. A selection unit, a voice recognition unit, and a voice operation unit are provided.

請求項１の発明によれば、異なる反響状態を想定した複数の音響モデルを音響モデル記憶部に予め記憶させておき、音響モデル選択部が、領域検出部により検出された話者の領域の反響状態に対応する音響モデルを選択し、選択された音響モデルを用いて音声認識を行っているので、浴室内を話者が移動した場合でも、話者が居る領域の反響状態に対応した音響モデルを選択することで、反響音の影響によって音声認識の認識精度が低下するのを抑制することができるという効果がある。   According to the first aspect of the present invention, a plurality of acoustic models assuming different reverberation states are stored in advance in the acoustic model storage unit, and the acoustic model selection unit echoes the region of the speaker detected by the region detection unit. Since the acoustic model corresponding to the state is selected and speech recognition is performed using the selected acoustic model, even if the speaker moves in the bathroom, the acoustic model corresponding to the echo state of the area where the speaker is located By selecting, there is an effect that it is possible to suppress a decrease in recognition accuracy of voice recognition due to the influence of reverberant sound.

ところで、話者の居る領域が同じ場合でも、話者の顔が向いている方向（つまり話者が発した音声の進行方向）によって反響状態が変化する可能性があるが、請求項２の発明によれば、領域検出部により検出された話者の居る領域と、方向検出部により検出された話者の顔の向きとに基づいて、音響モデル選択部が話者の発する声の残響状態に対応する音響モデルを選択しているので、反響音の影響による認識精度の低下をさらに抑制できるという効果がある。   By the way, even if the area where the speaker is present is the same, the echo state may change depending on the direction in which the speaker's face is facing (that is, the traveling direction of the voice uttered by the speaker). According to the above, the acoustic model selection unit changes the reverberation state of the voice of the speaker based on the region where the speaker is detected by the region detection unit and the direction of the speaker's face detected by the direction detection unit. Since the corresponding acoustic model is selected, it is possible to further suppress a reduction in recognition accuracy due to the influence of the echo sound.

請求項３の発明によれば、稼働中の浴室機器を使用する場合の予想位置を話者の居る領域として検出しているので、人体を検出するセンサなどを別途設置することなく、話者の位置を検出できるという効果がある。ここに、浴室機器を使用する場合の予想位置とは、稼働中の浴室機器を話者が使用する場合に、その話者が存在すると予想される位置を意味しており、例えばジェット噴流発生装置が稼働中であれば予想位置は浴槽であり、シャワー設備が稼働中であれば予想位置は洗い場となる。   According to the invention of claim 3, since the predicted position when using the bathroom equipment in operation is detected as an area where the speaker is present, the speaker's area can be detected without installing a sensor for detecting the human body separately. There is an effect that the position can be detected. Here, the expected position when using bathroom equipment means the position where the speaker is expected to be present when the speaker uses the bathroom equipment in operation, for example, a jet jet generator If is in operation, the expected position is a bathtub, and if the shower facility is in operation, the expected position is a washing place.

請求項４の発明によれば、請求項１乃至３の何れか１項に記載の音声検出部、領域検出部、音響モデル記憶部、音響モデル選択部、音声認識部、音声操作部を備えることで、反響音の影響により音声認識の認識率が低下するのを抑制した音声操作装置を実現することができる。   According to a fourth aspect of the present invention, the voice detection unit, the region detection unit, the acoustic model storage unit, the acoustic model selection unit, the voice recognition unit, and the voice operation unit according to any one of the first to third aspects are provided. Thus, it is possible to realize a voice operation device that suppresses a reduction in the recognition rate of voice recognition due to the influence of reverberant sound.

以下に本発明の実施の形態を図面に基づいて説明する。   Embodiments of the present invention will be described below with reference to the drawings.

（実施形態１）
本発明の実施形態１を図１〜図３に基づいて説明する。図２は本発明にかかる浴室装置Ａを適用した浴室１の構成を模式的に示した図であり、浴室１の内部には出入り口２に近い側に洗い場３が設けられ、出入り口２から遠い側に浴槽４が設置されている。浴槽４には、浴槽４に湯を張った状態で気泡を含むジェット噴流を発生させるジェット噴流発生装置（図示せず）が設けられている。また浴室１の天井５には、浴室１内の換気、暖房或いは浴室乾燥を行うための換気乾燥暖房機６と、浴室１内の照明を行う照明器具７とがそれぞれ設置されている。また浴室１の横壁８ａには、洗い場３側にシャワー設備９が設けられ、浴槽４側にテレビやビデオを視聴するための浴室テレビ１０が設置されている。また浴室１内の浴槽４に沿った横壁８ｂには、本発明の音声認識機能を有するコントローラ１１が設置されている。また浴室１の室外には、浴槽４内に溜める湯やシャワー設備９から出湯する湯を供給するための給湯器（図示せず）が設置されている。 (Embodiment 1)
Embodiment 1 of this invention is demonstrated based on FIGS. 1-3. FIG. 2 is a view schematically showing the configuration of the bathroom 1 to which the bathroom apparatus A according to the present invention is applied. The bathroom 1 is provided with a washing place 3 on the side close to the entrance 2 and on the side far from the entrance 2. There is a bathtub 4 installed. The bathtub 4 is provided with a jet jet generating device (not shown) that generates a jet jet containing bubbles in a state where hot water is filled in the bathtub 4. On the ceiling 5 of the bathroom 1, a ventilation / drying heater 6 for performing ventilation, heating or bathroom drying in the bathroom 1 and a lighting fixture 7 for illuminating the bathroom 1 are installed. Further, on the horizontal wall 8a of the bathroom 1, a shower facility 9 is provided on the washing room 3 side, and a bathroom TV 10 for viewing television and video is installed on the bathtub 4 side. A controller 11 having a voice recognition function of the present invention is installed on the horizontal wall 8b along the bathtub 4 in the bathroom 1. A hot water heater (not shown) for supplying hot water stored in the bathtub 4 or hot water discharged from the shower facility 9 is installed outside the bathroom 1.

図３はコントローラ１１の外観図であり、前面の形状が矩形状に形成されたボディ２０を有し、ボディ２０の前面を横壁８ｂの表面に露出させた状態で横壁８ｂに配設されている。ボディ２０の前面には、給湯器の動作状態や給湯温度の設定値などを示す液晶モニタ２１と、動作表示のための発光ダイオードＬＥＤと、マイクＭＣと、スピーカＳＰとが配置されている。またボディ２０の前面において、液晶モニタ２１の右側には、動作モードを設定モードに切り替えるためのメニュー釦２２ａと、設定項目や設定値を決定するための確定釦２２ｂと、１つ前の操作状態に戻すために操作する復帰釦２２ｃとが上下に並べて配置されており、各操作釦２２ａ〜２２ｃの前面には例えば「メニュー」「確定」「戻る」などの操作内容を示す文字が表示されている。さらに操作釦２２ａ〜２２ｃの下側には、設定モードにおいて設定項目を選択したり、設定値を変更したりするための上下左右のカーソル釦２３ａ〜２３ｄが配置されている。またボディ２０の前面において、液晶モニタ２１の左側には、例えば台所などに別置されたコントローラ（図示せず）からの操作に対して浴室側のコントローラ１１による操作を優先させるために操作する優先釦２２ｄと、浴槽４内に溜められている湯を温める際に押操作する追いだき釦２２ｅと、浴槽４内に所定温度の湯を所定量溜める際に押操作するふろ自動釦２２ｆと、台所に別置されたコントローラとの間でインターホン通話を行う際に操作する通話釦２２ｄとが上下に並べて配置されており、各操作釦２２ｄ〜２２ｇの前面には例えば「優先」「追いだき」「ふろ自動」「通話」といった操作内容を示す文字がそれぞれ表示されている。   FIG. 3 is an external view of the controller 11, which includes a body 20 having a front surface formed in a rectangular shape, and is disposed on the horizontal wall 8 b with the front surface of the body 20 exposed on the surface of the horizontal wall 8 b. . On the front surface of the body 20, a liquid crystal monitor 21 that indicates an operating state of the water heater, a set value of the hot water temperature, and the like, a light emitting diode LED for operation display, a microphone MC, and a speaker SP are arranged. On the front side of the body 20, on the right side of the liquid crystal monitor 21, a menu button 22a for switching the operation mode to the setting mode, a confirmation button 22b for determining setting items and setting values, and the previous operation state A return button 22c that is operated to return to the position is arranged side by side, and characters indicating operation contents such as “menu”, “confirm”, and “return” are displayed on the front of each operation button 22a to 22c. Yes. Further, below the operation buttons 22a to 22c, there are arranged cursor buttons 23a to 23d for selecting a setting item in the setting mode and changing a setting value. In addition, on the front side of the body 20, on the left side of the liquid crystal monitor 21, for example, priority is given to the operation by the controller 11 on the bathroom side over the operation from a controller (not shown) placed separately in the kitchen or the like. A button 22d, a follow-up button 22e that is pushed when warming the hot water stored in the bathtub 4, a bath automatic button 22f that is pushed when a predetermined amount of hot water is stored in the bathtub 4, and a kitchen Call buttons 22d that are operated when intercom calls are performed with a controller placed separately on the controller. The call buttons 22d are arranged side by side, and for example, "priority", "chase", " Characters indicating operation details such as “Buro automatic” and “call” are displayed.

また図１はコントローラ１１の要部のブロック図であり、音声命令の認識処理を行って浴室機器の操作を行う構成のみを図示してある。すなわち図１は浴室装置Ａに適用される音声操作装置Ｂの概略構成を示しており、音声操作装置Ｂは、浴室１内に設けられて入力された音声を電気信号に変換するマイクＭＣと、マイクＭＣから入力される電気信号（アナログ信号）をデジタル信号に変換するＡ／Ｄ変換部１２と、浴室１に設置された複数の浴室機器Ｃ（換気乾燥暖房機６、照明器具７、浴室テレビ１０、給湯機１８、ジェット噴流発生装置１９からなる）から現在稼働中の機器を検出する稼働状態検出部２４と、稼働状態検出部２４の検出結果に基づいて話者が居る領域を検出する領域検出部１３と、異なる反響状態をそれぞれ想定した複数の音響モデルＭ１，Ｍ２…Ｍｎを記憶する音響モデル記憶部１４と、音響モデル記憶部１４に記憶された複数の音響モデルＭ１，Ｍ２…Ｍｎから、領域検出部１３による検出領域の反響状態に対応した音響モデルを選択する音響モデル選択部１５と、Ａ／Ｄ変換部１２によりＡ／Ｄ変換された音声信号と音響モデル選択部１５により選択された音響モデルとをパターンマッチングすることによって音声命令の内容を認識する音声認識部１６と、音声認識部１６の認識結果に基づいて対応する浴室機器Ｃを操作する音声操作部１７とを備えている。   FIG. 1 is a block diagram of the main part of the controller 11 and shows only a configuration for performing voice command recognition processing and operating bathroom equipment. That is, FIG. 1 shows a schematic configuration of a voice operation device B applied to the bathroom device A, and the voice operation device B is provided in the bathroom 1 and converts a voice inputted into an electric signal into an electric signal, An A / D converter 12 that converts an electrical signal (analog signal) input from the microphone MC into a digital signal, and a plurality of bathroom devices C (ventilation dryer / heater 6, lighting fixture 7, bathroom television installed in the bathroom 1) 10, a hot water heater 18, and a jet jet generator 19), an operation state detection unit 24 that detects a currently operating device, and a region that detects a region where a speaker is present based on the detection result of the operation state detection unit 24 The detection unit 13, an acoustic model storage unit 14 that stores a plurality of acoustic models M 1, M 2,... Mn assuming different echo states, and a plurality of acoustic models M 1, M stored in the acoustic model storage unit 14. ... from Mn, an acoustic model selection unit 15 that selects an acoustic model corresponding to the echo state of the detection region by the region detection unit 13, and an audio signal and acoustic model selection unit 15 that have been A / D converted by the A / D conversion unit 12. A voice recognition unit 16 for recognizing the content of the voice command by pattern matching with the acoustic model selected by the voice model, and a voice operation unit 17 for operating the corresponding bathroom device C based on the recognition result of the voice recognition unit 16. I have.

マイクＭＣは、使用者の発した音声を電気信号に変換してＡ／Ｄ変換部１２に出力するために用いられ、このようなマイクＭＣとしてはコンデンサマイクや圧電マイクなど使用状態や使用環境に応じて適宜のものを使用することができる。   The microphone MC is used to convert the voice uttered by the user into an electrical signal and output it to the A / D converter 12. Such a microphone MC may be used in a usage state or usage environment such as a capacitor microphone or a piezoelectric microphone. An appropriate one can be used accordingly.

音響モデル記憶部１４には、浴室機器を操作するために用いる音声命令の認識処理に必要な音響モデルＭ１〜Ｍｎが格納されている。複数の音響モデルＭ１〜Ｍｎは、それぞれ異なる反響状態（例えば残響時間など）を想定して用意されており、個々の音響モデルとしては、例えば人間の発声の小さな単位（音素）の音響的特徴を表す隠れマルコフモデル（ＨＭＭ）などが用いられる。   The acoustic model storage unit 14 stores acoustic models M1 to Mn necessary for voice command recognition processing used to operate bathroom equipment. The plurality of acoustic models M1 to Mn are prepared assuming different reverberation states (for example, reverberation time), and each acoustic model has, for example, an acoustic feature of a small unit (phoneme) of human utterance. A hidden Markov model (HMM) to represent is used.

領域検出部１３は、稼働状態検出部２４により検出された稼働中の浴室機器を使用する場合の予想位置を話者の居る領域として検出する。浴室機器を使用する場合の予想位置とは、稼働中の機器を話者が使用する場合に話者が存在すると予想される位置のことを意味し、例えば稼働中の浴室機器がシャワー設備であれば、話者が洗い場３にいると予想され、ジェット噴流発生装置１９や浴室テレビ１０であれば浴槽４内にいると予想される。   The area detection unit 13 detects an expected position when the bathroom device in operation detected by the operation state detection unit 24 is used as an area where a speaker is present. The expected position when using bathroom equipment means the position where the speaker is expected to be present when the speaker uses the operating equipment. For example, the operating bathroom equipment may be a shower facility. For example, the speaker is expected to be in the washing place 3, and the jet jet generator 19 and the bathroom television 10 are expected to be in the bathtub 4.

ここで、浴室１は狭く閉じた空間であり、反射の強い環境であるため、浴室１内で話者が発した音声は残響音の影響を大きく受けて、音声に歪みが生じる。しかも浴室１内では話者が居る場所に応じて反響状態が大きく異なるため、反響音が音声に与える影響も異なることが予想される。そこで本実施形態では、音響モデル記憶部１４に、異なる反響状態をそれぞれ想定した複数の音響モデルＭ１〜Ｍｎを予め用意しておき、音響モデル選択部１５が、領域検出部１３により検出された領域をもとに、話者がいる領域の反響状態に近い音響モデルを音響モデル記憶部１４に登録された音響モデルの中から選択している。したがって、浴室１内で話者が移動したとしても、話者が居る領域の反響状態に対応した音響モデルを選択して使用することができ、音声認識部１６が、音響モデル選択部１５により選択された音響モデルを用いて音声認識を行うことで、反響音の影響による音声認識率の低下を抑制することができる。そして、音声操作部１７は、音声認識部１６の認識結果に基づいて対応する浴室機器Ｃを操作しているので、音声の誤認識によって意図した操作が行われるのを防止し、意図した操作を行わせることができる。また、領域検出部２４は、稼働中の浴室機器を使用する場合の予想位置を話者の居る領域として検出しており、コントローラ１１では音声操作部１７の操作対象である浴室機器Ｃの稼働状態を把握できるので、人体を検出するセンサなどを別途設置することなく、話者の位置を検出することができる。   Here, since the bathroom 1 is a narrow and closed space and is a highly reflective environment, the voice uttered by the speaker in the bathroom 1 is greatly affected by the reverberant sound, and the voice is distorted. Moreover, since the echo state varies greatly depending on the location of the speaker in the bathroom 1, it is expected that the influence of the echo sound on the voice will also be different. Therefore, in this embodiment, a plurality of acoustic models M1 to Mn each assuming different echo states are prepared in advance in the acoustic model storage unit 14, and the acoustic model selection unit 15 detects the region detected by the region detection unit 13. Based on the above, the acoustic model close to the echo state in the area where the speaker is present is selected from the acoustic models registered in the acoustic model storage unit 14. Therefore, even if the speaker moves in the bathroom 1, it is possible to select and use an acoustic model corresponding to the echo state of the area where the speaker is present, and the speech recognition unit 16 selects the acoustic model by the acoustic model selection unit 15. By performing speech recognition using the made acoustic model, it is possible to suppress a decrease in speech recognition rate due to the influence of reverberant sound. And since the audio | voice operation part 17 is operating the corresponding bathroom apparatus C based on the recognition result of the audio | voice recognition part 16, it prevents that the intended operation is performed by misrecognition of an audio | voice, and performs the intended operation. Can be done. Further, the area detection unit 24 detects an expected position when the bathroom device in operation is used as a region where the speaker is present, and the controller 11 operates the operating state of the bathroom device C that is the operation target of the voice operation unit 17. Therefore, the position of the speaker can be detected without separately installing a sensor or the like for detecting a human body.

（実施形態２）
本発明の実施形態２を図４及び図５に基づいて説明する。尚、領域検出部１３による話者の検知方法が異なる点を除いては上述の実施形態１と同様であるので、共通する構成要素には同一の符号を付して、その説明は省略する。 (Embodiment 2)
A second embodiment of the present invention will be described with reference to FIGS. Since the method is the same as that of the first embodiment except that the method of detecting the speaker by the region detection unit 13 is different, common constituent elements are denoted by the same reference numerals and description thereof is omitted.

上述の実施形態１では、領域検出部１３が稼働状態検出部２４の検出結果に基づいて話者の居る領域を検出しているのに対して、本実施形態では図４に示すように浴室１に複数の人感センサ１３ａと、ドアセンサ１３ｂを設置し、両センサ１３ａ，１３ｂの検出結果に基づいて領域検出部１３が話者の居る領域を検出するようにしている。   In the first embodiment described above, the area detecting unit 13 detects the area where the speaker is present based on the detection result of the operating state detecting unit 24, whereas in the present embodiment, as shown in FIG. A plurality of human sensors 13a and a door sensor 13b are installed, and based on the detection results of both sensors 13a and 13b, the region detector 13 detects the region where the speaker is present.

人感センサ１３ａは、例えば焦電型赤外線検出素子を備え、人体から放射される熱線を検出することによって検知領域における人の存否を検出する。ここで浴室１の天井５に複数個（例えば３個）の人感センサ１３ａを設置し、それぞれ浴室１内に設定された検知領域Ｄ１〜Ｄ３（図５参照）における人の存否を検出するようになっており、領域検出部１３では、検知信号を発した人感センサ１３ａの検知領域を話者のいる領域として検出する。   The human sensor 13a includes, for example, a pyroelectric infrared detection element, and detects the presence or absence of a person in the detection region by detecting heat rays emitted from the human body. Here, a plurality (for example, three) of human sensors 13a are installed on the ceiling 5 of the bathroom 1, and the presence / absence of a person in the detection areas D1 to D3 (see FIG. 5) set in the bathroom 1 is detected. The area detection unit 13 detects the detection area of the human sensor 13a that has issued the detection signal as an area where a speaker is present.

またドアセンサ１３ｂは、浴室１の出入り口２の開閉状態を検出するマグネットセンサなどからなり、領域検出部１３ではドアセンサ１３ｂから検知信号が入力されると、出入り口２の近傍を話者がいる領域と判断する。   The door sensor 13b includes a magnet sensor that detects the open / closed state of the entrance / exit 2 of the bathroom 1. When the detection signal is input from the door sensor 13b, the area detection unit 13 determines that the vicinity of the entrance / exit 2 is an area where a speaker is present. To do.

このように本実施形態では領域検出部１３が、人感センサ１３ａやドアセンサ１３ｂからの検知入力に基づいて、浴室１内で話者が居る領域を検出しており、実施形態１で説明したように音響モデル選択部１５が領域検出部１３の検出結果を用いて話者の居る領域に対応した音響モデルを選択しているので、話者の居る領域の反響状態に対応した音響モデルが選択でき、反響音の影響によって音声認識の認識率が低下するのを抑制することができる。   Thus, in this embodiment, the area detection unit 13 detects an area where a speaker is present in the bathroom 1 based on the detection input from the human sensor 13a and the door sensor 13b, as described in the first embodiment. Since the acoustic model selection unit 15 selects the acoustic model corresponding to the region where the speaker is present using the detection result of the region detection unit 13, the acoustic model corresponding to the echo state of the region where the speaker is present can be selected. Thus, it is possible to suppress a reduction in the recognition rate of voice recognition due to the influence of reverberant sound.

なお本実施形態では人感センサ１３ａとして焦電型の赤外線検出素子を用いたセンサを用いているが、人感センサ１３ａをＰＩＲセンサに限定する趣旨のものではなく、例えば超音波を用いて検出領域における物体（すなわち人体）の存否を検出する超音波センサや、ＬＥＤ距離計測方式により検知領域における物体の位置や形状を検出する距離画像センサや、浴室１の床面に設置されて圧力変化を検出することにより人の存否を検出する圧力センサなどを用いても良い。   In the present embodiment, a sensor using a pyroelectric infrared detection element is used as the human sensor 13a. However, the human sensor 13a is not limited to a PIR sensor, and is detected using, for example, an ultrasonic wave. An ultrasonic sensor that detects the presence or absence of an object (that is, a human body) in the area, a distance image sensor that detects the position or shape of the object in the detection area by an LED distance measurement method, or a pressure change that is installed on the floor of the bathroom 1 You may use the pressure sensor etc. which detect the presence or absence of a person by detecting.

（実施形態３）
本発明の実施形態３を図６に基づいて説明する。尚、領域検出部１３の代わりに領域・方向検出部２５を設けた点を除いては上述の実施形態１と同様であるので、共通する構成要素には同一の符号を付して、その説明は省略する。 (Embodiment 3)
Embodiment 3 of the present invention will be described with reference to FIG. In addition, since it is the same as that of the above-mentioned Embodiment 1 except the point which provided the area | region / direction detection part 25 instead of the area | region detection part 13, the same code | symbol is attached | subjected to the common component and the description is given. Is omitted.

上述の実施形態１では、領域検出部１３が稼働状態検出部２４の検出結果に基づいて話者の居る領域を検出しているのに対して、本実施形態では浴室１に内部を撮影するカメラ２６ａ，２６ｂを設置し、領域・方向検出部２５が、カメラ２６ａ，２６ｂにより撮影された画像をもとに話者の居る領域と、話者の顔が向いている方向とを検出するようになっている。   In the first embodiment described above, the area detection unit 13 detects the area where the speaker is present based on the detection result of the operating state detection unit 24, whereas in the present embodiment, the camera that images the interior of the bathroom 1 26a and 26b are installed, and the area / direction detection unit 25 detects the area where the speaker is located and the direction in which the speaker's face is facing based on the images taken by the cameras 26a and 26b. It has become.

２台のカメラ２６ａ，２６ｂは例えばＣＣＤ撮像素子を用いたテレビカメラからなり、浴室１の天井５付近において出入り口２側と反対側とにそれぞれ設置されており、浴室１の内部を２方向から撮影できるようになっている。なおカメラ２６ａ，２６ｂの台数や設置位置は上記の形態に限定されるものではなく、浴室１内の任意の場所を複数の方向から撮影できるのであれば、その台数や配置は問わない。   The two cameras 26a and 26b are composed of, for example, a television camera using a CCD image sensor, and are installed on the opposite side to the entrance 2 side in the vicinity of the ceiling 5 of the bathroom 1, so that the inside of the bathroom 1 is photographed from two directions. It can be done. Note that the number and installation positions of the cameras 26a and 26b are not limited to the above-described forms, and any number and arrangement are possible as long as an arbitrary place in the bathroom 1 can be photographed from a plurality of directions.

領域・方向検出部２５は、カメラ２６ａ，２６ｂから入力される画像信号に２値化処理を施し、話者が居ないときの画像との差分画像を求めた後、人体の頭部を表すテンプレート画像とのマッチング処理を行って、話者がいる領域を求めるとともに、頭部（すなわち顔）の向きを検出して、検出結果を音響モデル選択部１５に出力する。   The region / direction detection unit 25 performs binarization processing on the image signals input from the cameras 26a and 26b, obtains a difference image from the image when there is no speaker, and then represents a template representing the head of the human body The matching process with the image is performed to obtain the area where the speaker is present, the direction of the head (ie, the face) is detected, and the detection result is output to the acoustic model selection unit 15.

ところで、話者の居る領域が同じ場合でも、話者の顔が向いている方向（つまり話者が発した音声の進行方向）によって反響状態が変化する可能性があるが、本実施形態では音響モデル選択部１５が、領域・方向検出部により検出された話者の居る領域と、話者の顔が向いている方向（つまり話者の音声の進行方向）とをもとに、話者が発する音声の反響状態に近い音響モデルを選択しているので、反響音の影響による認識精度の低下をさらに抑制することができる。   By the way, even if the area where the speaker is located is the same, the echo state may change depending on the direction in which the speaker's face is facing (that is, the traveling direction of the voice uttered by the speaker). Based on the region where the speaker is detected by the region / direction detection unit and the direction in which the speaker's face is facing (that is, the direction in which the speaker's voice travels), the model selection unit 15 Since the acoustic model close to the echo state of the emitted voice is selected, it is possible to further suppress the degradation of recognition accuracy due to the influence of the echo sound.

実施形態１の浴室装置のシステム構成を示すブロック図である。It is a block diagram which shows the system configuration | structure of the bathroom apparatus of Embodiment 1. 同上の浴室装置の設置例を示す外観図である。It is an external view which shows the example of installation of a bathroom apparatus same as the above. 同上に用いるコントローラの正面図である。It is a front view of the controller used for the same as the above. 実施形態２の浴室装置のシステム構成を示すブロック図である。It is a block diagram which shows the system configuration | structure of the bathroom apparatus of Embodiment 2. 同上に用いる人感センサの検知領域を説明する説明図である。It is explanatory drawing explaining the detection area | region of the human sensitive sensor used for the same as the above. 実施形態３の浴室装置のシステム構成を示すブロック図である。It is a block diagram which shows the system configuration | structure of the bathroom apparatus of Embodiment 3.

符号の説明Explanation of symbols

Ａ 浴室装置
Ｂ 音声操作装置
Ｃ 浴室機器
Ｍ１〜Ｍｎ 音響モデル
ＭＣ マイク
１３ 領域検出部
１４ 音響モデル記憶部
１５ 音響モデル選択部
１６ 音声認識部
１７ 音声操作部
２４ 稼働状態検出部
A bathroom device B voice operation device C bathroom equipment M1 to Mn acoustic model MC microphone 13 region detection unit 14 acoustic model storage unit 15 acoustic model selection unit 16 voice recognition unit 17 voice operation unit 24 operating state detection unit

Claims (4)

浴室に設けられた複数の浴室機器と、前記浴室に設けられた音声検出部と、前記浴室内で話者がいる領域を検出する領域検出部と、異なる反響状態をそれぞれ想定した複数の音響モデルを記憶する音響モデル記憶部と、音響モデル記憶部に記憶された複数の音響モデルから、領域検出部による検出領域の反響状態に対応した音響モデルを選択する音響モデル選択部と、音響モデル選択部により選択された音響モデルを用いて音声検出部が検出した音声の内容を認識する音声認識部と、音声認識部により認識された音声の内容にしたがって対応する浴室機器を操作する音声操作部とを備えて成ることを特徴とする浴室装置。   A plurality of bathroom models provided in a bathroom, a voice detection unit provided in the bathroom, a region detection unit for detecting a region where a speaker is present in the bathroom, and a plurality of acoustic models each assuming different echo states An acoustic model storage unit that stores the acoustic model, an acoustic model selection unit that selects an acoustic model corresponding to the reverberation state of the detection region by the region detection unit from a plurality of acoustic models stored in the acoustic model storage unit, and an acoustic model selection unit A voice recognition unit that recognizes the content of the voice detected by the voice detection unit using the acoustic model selected by the voice model, and a voice operation unit that operates a corresponding bathroom device according to the voice content recognized by the voice recognition unit. A bathroom apparatus characterized by comprising. 前記話者の顔が向いている方向を検出する方向検出部を設け、前記音響モデル選択部は、領域検出部による検出領域と、方向検出部による検出方向とをもとに、前記話者が発する声の残響状態に対応する音響モデルを選択することを特徴とする請求項１記載の浴室装置。   A direction detection unit that detects a direction in which the speaker's face is facing is provided, and the acoustic model selection unit is configured to detect the speaker based on a detection region by the region detection unit and a detection direction by the direction detection unit. The bathroom apparatus according to claim 1, wherein an acoustic model corresponding to a reverberation state of a voice to be emitted is selected. 前記各浴室機器の稼働状態を検出する稼働状態検出部を設け、前記領域検出部は、稼働状態検出部により検出された稼働中の浴室機器を使用する場合の予想位置を話者の居る領域として検出することを特徴とする請求項１又は２記載の浴室装置。   An operation state detection unit that detects the operation state of each bathroom device is provided, and the region detection unit sets an expected position when the bathroom device in operation detected by the operation state detection unit is used as a region where a speaker is present. The bathroom apparatus according to claim 1, wherein the bathroom apparatus is detected. 請求項１乃至３の何れか１項に記載の浴室装置に用いられる音声操作装置であって、前記音声検出部と、前記領域検出部と、前記音響モデル記憶部と、前記音響モデル選択部と、前記音声認識部と、前記音声操作部とを備えて成ることを特徴とする音声操作装置。
It is an audio | voice operating device used for the bathroom apparatus of any one of Claim 1 thru | or 3, Comprising: The said audio | voice detection part, the said area | region detection part, the said acoustic model memory | storage part, and the said acoustic model selection part A voice operation device comprising: the voice recognition unit; and the voice operation unit.
JP2006089560A 2006-03-28 2006-03-28 Voice control device Expired - Fee Related JP4784366B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2006089560A JP4784366B2 (en) 2006-03-28 2006-03-28 Voice control device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2006089560A JP4784366B2 (en) 2006-03-28 2006-03-28 Voice control device

Publications (2)

Publication Number Publication Date
JP2007264328A true JP2007264328A (en) 2007-10-11
JP4784366B2 JP4784366B2 (en) 2011-10-05

Family

ID=38637375

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2006089560A Expired - Fee Related JP4784366B2 (en) 2006-03-28 2006-03-28 Voice control device

Country Status (1)

Country Link
JP (1) JP4784366B2 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009223170A (en) * 2008-03-18 2009-10-01 Advanced Telecommunication Research Institute International Speech recognition system
KR20190110728A (en) * 2018-03-21 2019-10-01 현대모비스 주식회사 Apparatus for recognizing voice speaker and method the same
WO2021025343A1 (en) * 2019-08-08 2021-02-11 삼성전자주식회사 Electronic device and method for recognizing voice by same
EP3653945A4 (en) * 2017-07-14 2021-07-28 Daikin Industries, Ltd. Air conditioner, air-conditioning system, communication system, control system, machinery control system, machinery management system, and sound information analysis system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000066698A (en) * 1998-08-19 2000-03-03 Nippon Telegr & Teleph Corp <Ntt> Sound recognizer
JP2003345389A (en) * 2002-05-22 2003-12-03 Nissan Motor Co Ltd Voice recognition device
JP2004117724A (en) * 2002-09-25 2004-04-15 Matsushita Electric Works Ltd Speech recognition device
JP2004198656A (en) * 2002-12-17 2004-07-15 Japan Science & Technology Agency Robot audio-visual system
JP2004206063A (en) * 2002-10-31 2004-07-22 Seiko Epson Corp Sound model generating method, speech recognition device, and vehicle with speech recognition device
JP2005090837A (en) * 2003-09-17 2005-04-07 Noritz Corp Hot water system
WO2005048239A1 (en) * 2003-11-12 2005-05-26 Honda Motor Co., Ltd. Speech recognition device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000066698A (en) * 1998-08-19 2000-03-03 Nippon Telegr & Teleph Corp <Ntt> Sound recognizer
JP2003345389A (en) * 2002-05-22 2003-12-03 Nissan Motor Co Ltd Voice recognition device
JP2004117724A (en) * 2002-09-25 2004-04-15 Matsushita Electric Works Ltd Speech recognition device
JP2004206063A (en) * 2002-10-31 2004-07-22 Seiko Epson Corp Sound model generating method, speech recognition device, and vehicle with speech recognition device
JP2004198656A (en) * 2002-12-17 2004-07-15 Japan Science & Technology Agency Robot audio-visual system
JP2005090837A (en) * 2003-09-17 2005-04-07 Noritz Corp Hot water system
WO2005048239A1 (en) * 2003-11-12 2005-05-26 Honda Motor Co., Ltd. Speech recognition device

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009223170A (en) * 2008-03-18 2009-10-01 Advanced Telecommunication Research Institute International Speech recognition system
EP3653945A4 (en) * 2017-07-14 2021-07-28 Daikin Industries, Ltd. Air conditioner, air-conditioning system, communication system, control system, machinery control system, machinery management system, and sound information analysis system
CN114893823A (en) * 2017-07-14 2022-08-12 大金工业株式会社 Air conditioning system
CN114893823B (en) * 2017-07-14 2023-06-27 大金工业株式会社 Air conditioning system
KR20190110728A (en) * 2018-03-21 2019-10-01 현대모비스 주식회사 Apparatus for recognizing voice speaker and method the same
KR102550598B1 (en) 2018-03-21 2023-07-04 현대모비스 주식회사 Apparatus for recognizing voice speaker and method the same
WO2021025343A1 (en) * 2019-08-08 2021-02-11 삼성전자주식회사 Electronic device and method for recognizing voice by same
US11551687B2 (en) 2019-08-08 2023-01-10 Samsung Electronics Co., Ltd. Electronic device and method for speech recognition of the same

Also Published As

Publication number Publication date
JP4784366B2 (en) 2011-10-05

Similar Documents

Publication Publication Date Title
KR102293063B1 (en) Customizable wake-up voice commands
CN106463114B (en) Information processing apparatus, control method, and program storage unit
KR101556173B1 (en) Apparatus and method for driving electric device using speech recognition
WO2016157662A1 (en) Information processing device, control method, and program
US9111326B1 (en) Designation of zones of interest within an augmented reality environment
JP2017117371A (en) Control method, control device, and program
JP6433903B2 (en) Speech recognition method and speech recognition apparatus
CN111868824A (en) Context aware control of smart devices
JP2005284492A (en) Operating device using voice
EP3602241B1 (en) Method and apparatus for interaction with an intelligent personal assistant
US20180090138A1 (en) System and method for localization and acoustic voice interface
JP2011081541A (en) Input device and control method thereof
JP2009192942A (en) Voice interaction apparatus and support method
JP4784366B2 (en) Voice control device
WO2017141530A1 (en) Information processing device, information processing method and program
US20200135202A1 (en) Electronic device and control method thereof
JP2000347692A (en) Person detecting method, person detecting device, and control system using it
US20220270601A1 (en) Multi-modal smart audio device system attentiveness expression
US11657821B2 (en) Information processing apparatus, information processing system, and information processing method to execute voice response corresponding to a situation of a user
JP2009080183A (en) Speech recognition control device
JP4760477B2 (en) Bathroom device and voice operation system used therefor
JP2007179857A (en) Apparatus controller
JP2008268517A (en) Operating device with speech recognition function
JP2009109536A (en) Voice recognition system and voice recognizer
JP4915665B2 (en) Controller with voice recognition function

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20081210

RD04 Notification of resignation of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7424

Effective date: 20100802

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20101029

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20101109

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20110111

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20110208

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20110509

A911 Transfer to examiner for re-examination before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A911

Effective date: 20110518

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20110614

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20110627

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140722

Year of fee payment: 3

LAPS Cancellation because of no payment of annual fees