DE60110315T2 - Trainieren von akustischen Modellen zur Widerstandsfähigkeit gegen Rauschen - Google Patents

Trainieren von akustischen Modellen zur Widerstandsfähigkeit gegen Rauschen Download PDF

Info

Publication number
DE60110315T2
DE60110315T2 DE60110315T DE60110315T DE60110315T2 DE 60110315 T2 DE60110315 T2 DE 60110315T2 DE 60110315 T DE60110315 T DE 60110315T DE 60110315 T DE60110315 T DE 60110315T DE 60110315 T2 DE60110315 T2 DE 60110315T2
Authority
DE
Germany
Prior art keywords
samples
clusters
noise
training
acoustic model
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.)
Expired - Lifetime
Application number
DE60110315T
Other languages
German (de)
English (en)
Other versions
DE60110315D1 (de
Inventor
Maki Yamada
Masakatsu Zama-shi Hoshimi
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 Corp
Original Assignee
Matsushita Electric Industrial Co 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 Industrial Co Ltd filed Critical Matsushita Electric Industrial Co Ltd
Application granted granted Critical
Publication of DE60110315D1 publication Critical patent/DE60110315D1/de
Publication of DE60110315T2 publication Critical patent/DE60110315T2/de
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G10L2015/0631—Creating reference templates; Clustering
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G10L2015/0638—Interactive procedures
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Stored Programmes (AREA)
DE60110315T 2000-06-28 2001-06-15 Trainieren von akustischen Modellen zur Widerstandsfähigkeit gegen Rauschen Expired - Lifetime DE60110315T2 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2000194196 2000-06-28
JP2000194196A JP4590692B2 (ja) 2000-06-28 2000-06-28 音響モデル作成装置及びその方法

Publications (2)

Publication Number Publication Date
DE60110315D1 DE60110315D1 (de) 2005-06-02
DE60110315T2 true DE60110315T2 (de) 2006-03-09

Family

ID=18693064

Family Applications (1)

Application Number Title Priority Date Filing Date
DE60110315T Expired - Lifetime DE60110315T2 (de) 2000-06-28 2001-06-15 Trainieren von akustischen Modellen zur Widerstandsfähigkeit gegen Rauschen

Country Status (5)

Country Link
US (1) US6842734B2 (enExample)
EP (1) EP1168301B1 (enExample)
JP (1) JP4590692B2 (enExample)
CN (1) CN1162839C (enExample)
DE (1) DE60110315T2 (enExample)

Families Citing this family (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7209881B2 (en) * 2001-12-20 2007-04-24 Matsushita Electric Industrial Co., Ltd. Preparing acoustic models by sufficient statistics and noise-superimposed speech data
US6952674B2 (en) * 2002-01-07 2005-10-04 Intel Corporation Selecting an acoustic model in a speech recognition system
JP3885002B2 (ja) * 2002-06-28 2007-02-21 キヤノン株式会社 情報処理装置およびその方法
JP4352790B2 (ja) * 2002-10-31 2009-10-28 セイコーエプソン株式会社 音響モデル作成方法および音声認識装置ならびに音声認識装置を有する乗り物
US7365577B2 (en) * 2002-11-15 2008-04-29 Telebyte, Inc. Noise waveform generator with spectrum control
GB2401469B (en) * 2003-05-09 2006-11-22 Domain Dynamics Ltd Pattern recognition
JP4548646B2 (ja) 2003-09-12 2010-09-22 株式会社エヌ・ティ・ティ・ドコモ 音声モデルの雑音適応化システム、雑音適応化方法、及び、音声認識雑音適応化プログラム
WO2005098820A1 (ja) * 2004-03-31 2005-10-20 Pioneer Corporation 音声認識装置及び音声認識方法
JP4763387B2 (ja) * 2005-09-01 2011-08-31 旭化成株式会社 パターンモデル生成装置、パターンモデル評価装置およびパターン認識装置
KR100679051B1 (ko) * 2005-12-14 2007-02-05 삼성전자주식회사 복수의 신뢰도 측정 알고리즘을 이용한 음성 인식 장치 및방법
TW200926142A (en) * 2007-12-12 2009-06-16 Inst Information Industry A construction method of English recognition variation pronunciation models
JP5302092B2 (ja) * 2009-05-12 2013-10-02 株式会社レイトロン 音声認識モデルパラメータ作成装置、音声認識モデルパラメータ作成方法および音声認識装置
US10013641B2 (en) * 2009-09-28 2018-07-03 Oracle International Corporation Interactive dendrogram controls
US20110078194A1 (en) * 2009-09-28 2011-03-31 Oracle International Corporation Sequential information retrieval
US10552710B2 (en) * 2009-09-28 2020-02-04 Oracle International Corporation Hierarchical sequential clustering
CN103971685B (zh) * 2013-01-30 2015-06-10 腾讯科技（深圳）有限公司 语音命令识别方法和系统
CN103971677B (zh) * 2013-02-01 2015-08-12 腾讯科技（深圳）有限公司 一种声学语言模型训练方法和装置
US9396723B2 (en) 2013-02-01 2016-07-19 Tencent Technology (Shenzhen) Company Limited Method and device for acoustic language model training
US20140278415A1 (en) * 2013-03-12 2014-09-18 Motorola Mobility Llc Voice Recognition Configuration Selector and Method of Operation Therefor
US9552825B2 (en) * 2013-04-17 2017-01-24 Honeywell International Inc. Noise cancellation for voice activation
WO2014182453A2 (en) * 2013-05-06 2014-11-13 Motorola Mobility Llc Method and apparatus for training a voice recognition model database
CN103280215B (zh) * 2013-05-28 2016-03-23 北京百度网讯科技有限公司 一种音频特征库建立方法及装置
US9336781B2 (en) * 2013-10-17 2016-05-10 Sri International Content-aware speaker recognition
GB2532041B (en) * 2014-11-06 2019-05-29 Imagination Tech Ltd Comfort noise generation
KR102167719B1 (ko) * 2014-12-08 2020-10-19 삼성전자주식회사 언어 모델 학습 방법 및 장치, 음성 인식 방법 및 장치
JP6580882B2 (ja) * 2015-06-24 2019-09-25 株式会社東芝 音声認識結果出力装置、音声認識結果出力方法及び音声認識結果出力プログラム
CN105448303B (zh) * 2015-11-27 2020-02-04 百度在线网络技术（北京）有限公司 语音信号的处理方法和装置
US9922664B2 (en) * 2016-03-28 2018-03-20 Nuance Communications, Inc. Characterizing, selecting and adapting audio and acoustic training data for automatic speech recognition systems
CN107564513B (zh) 2016-06-30 2020-09-08 阿里巴巴集团控股有限公司 语音识别方法及装置
CN108335694B (zh) * 2018-02-01 2021-10-15 北京百度网讯科技有限公司 远场环境噪声处理方法、装置、设备和存储介质
US11011162B2 (en) 2018-06-01 2021-05-18 Soundhound, Inc. Custom acoustic models
CN110942763B (zh) * 2018-09-20 2023-09-12 阿里巴巴集团控股有限公司 语音识别方法及装置
CN110599751A (zh) * 2019-08-26 2019-12-20 恒大智慧科技有限公司 一种危险报警方法、装置、计算机设备及存储介质
CN110459219A (zh) * 2019-08-26 2019-11-15 恒大智慧科技有限公司 一种危险报警方法、装置、计算机设备及存储介质
WO2021074973A1 (ja) * 2019-10-15 2021-04-22 日本電気株式会社 モデル生成方法、モデル生成装置、プログラム
CN111369979B (zh) * 2020-02-26 2023-12-19 广州市百果园信息技术有限公司 训练样本获取方法、装置、设备及计算机存储介质
WO2021258240A1 (en) * 2020-06-22 2021-12-30 Qualcomm Incorporated Voice or speech recognition in noisy environments
US11765501B2 (en) * 2021-03-10 2023-09-19 Honeywell International Inc. Video surveillance system with audio analytics adapted to a particular environment to aid in identifying abnormal events in the particular environment
EP4512579A4 (en) 2022-07-18 2025-07-09 Samsung Electronics Co Ltd LEARNING DATA ACQUISITION ROBOT AND ITS CONTROL METHOD

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS58105295A (ja) 1981-12-18 1983-06-23 株式会社日立製作所 音声標準パタン作成方法
JPH06138895A (ja) * 1992-10-26 1994-05-20 Sharp Corp 音声認識装置
DE4325404C2 (de) 1993-07-29 2002-04-11 Tenovis Gmbh & Co Kg Verfahren zum Ermitteln und Klassifizieren von Störgeräuschtypen
NZ316124A (en) 1995-08-24 2000-02-28 British Telecomm Pattern recognition for speech recognising noise signals signatures
US5806029A (en) * 1995-09-15 1998-09-08 At&T Corp Signal conditioned minimum error rate training for continuous speech recognition
JPH09198079A (ja) * 1996-01-12 1997-07-31 Brother Ind Ltd 音声認識装置
JPH10232694A (ja) * 1997-02-19 1998-09-02 Matsushita Electric Ind Co Ltd 音声認識装置および音声認識方法
US6381569B1 (en) 1998-02-04 2002-04-30 Qualcomm Incorporated Noise-compensated speech recognition templates
US6782361B1 (en) * 1999-06-18 2004-08-24 Mcgill University Method and apparatus for providing background acoustic noise during a discontinued/reduced rate transmission mode of a voice transmission system

Also Published As

Publication number Publication date
US20020055840A1 (en) 2002-05-09
DE60110315D1 (de) 2005-06-02
JP2002014692A (ja) 2002-01-18
US6842734B2 (en) 2005-01-11
EP1168301B1 (en) 2005-04-27
JP4590692B2 (ja) 2010-12-01
EP1168301A1 (en) 2002-01-02
CN1331467A (zh) 2002-01-16
CN1162839C (zh) 2004-08-18

Similar Documents

Publication Publication Date Title
DE60110315T2 (de) Trainieren von akustischen Modellen zur Widerstandsfähigkeit gegen Rauschen
DE69311303T2 (de) Sprachtrainingshilfe für kinder.
DE69707876T2 (de) Verfahren und vorrichtung fuer dynamisch eingestelltes training zur spracherkennung
DE69427083T2 (de) Spracherkennungssystem für mehrere sprachen
DE69629763T2 (de) Verfahren und Vorrichtung zur Ermittlung von Triphone Hidden Markov Modellen (HMM)
DE69719236T2 (de) Verfahren und System zur Spracherkennung mittels verborgener Markoff-Modelle mit kontinuierlichen Ausgangswahrscheinlichkeiten
DE69719270T2 (de) Sprachsynthese unter Verwendung von Hilfsinformationen
DE602004000382T2 (de) Rauschadaptierung zur Spracherkennung
DE102017124264B4 (de) Computerimplementiertes Verfahren und Rechensystem zum Bestimmen phonetischer Beziehungen
DE69719654T2 (de) Grundfrequenzmuster enthaltende Prosodie-Datenbanken für die Sprachsynthese
DE69031165T2 (de) System und methode zur text-sprache-umsetzung mit hilfe von kontextabhängigen vokalallophonen
DE60213595T2 (de) Hintergrundlernen von sprecherstimmen
DE69226594T2 (de) Spracherkennungseinrichtung mit Sprachkodierer, der Rangstufen von akustischen Prototypen ausgibt.
DE69718284T2 (de) Sprachsynthesesystem und Wellenform-Datenbank mit verringerter Redundanz
DE60020434T2 (de) Erzeugung und Synthese von Prosodie-Mustern
DE3878071T2 (de) Sprachnormierung durch adaptive klassifizierung.
DE60305568T2 (de) Schlüsselworterkennung in einem Sprachsignal
DE10306599B4 (de) Benutzeroberfläche, System und Verfahren zur automatischen Benennung von phonischen Symbolen für Sprachsignale zum Korrigieren von Aussprache
DE112013007617B4 (de) Spracherkennungsvorrichtung und Spracherkennungsverfahren
EP3291234B1 (de) Verfahren zum beurteilen einer qualität eines stimmeinsatzes eines sprechenden
WO2000054256A1 (de) Verfahren und anordnung zur ermittlung einer merkmalsbeschreibung eines sprachsignals
DE60108104T2 (de) Verfahren zur Sprecheridentifikation
DE60302478T2 (de) Vorrichtung und Verfahren zur Sprachinformationserkennung unter Verwendung der Analyse myoelektrischer Signale
DE212016000292U1 (de) System zur Text-zu-Sprache-Leistungsbewertung
DE60133537T2 (de) Automatisches umtrainieren eines spracherkennungssystems

Legal Events

Date Code Title Description
8364 No opposition during term of opposition
8327 Change in the person/name/address of the patent owner

Owner name: PANASONIC CORP., KADOMA, OSAKA, JP