DE69626954D1 - Signalkonditioniertes training mit minimaler fehlerrate für kontinuierliche spracherkennung - Google Patents

Signalkonditioniertes training mit minimaler fehlerrate für kontinuierliche spracherkennung

Info

Publication number
DE69626954D1
DE69626954D1 DE69626954T DE69626954T DE69626954D1 DE 69626954 D1 DE69626954 D1 DE 69626954D1 DE 69626954 T DE69626954 T DE 69626954T DE 69626954 T DE69626954 T DE 69626954T DE 69626954 D1 DE69626954 D1 DE 69626954D1
Authority
DE
Germany
Prior art keywords
signal
error rate
voice recognition
minimum error
continuous voice
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
DE69626954T
Other languages
English (en)
Inventor
Rolfe Buhrke
Wu Chou
G Rahim
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.)
AT&T Corp
Original Assignee
AT&T 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 AT&T Corp filed Critical AT&T Corp
Application granted granted Critical
Publication of DE69626954D1 publication Critical patent/DE69626954D1/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
    • G10L15/08—Speech classification or search
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]
    • G10L15/144—Training of HMMs
    • 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
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • 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
    • G10L21/0272—Voice signal separating

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)
  • Detection And Prevention Of Errors In Transmission (AREA)
  • Complex Calculations (AREA)
DE69626954T 1995-09-15 1996-09-12 Signalkonditioniertes training mit minimaler fehlerrate für kontinuierliche spracherkennung Expired - Lifetime DE69626954D1 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/528,821 US5806029A (en) 1995-09-15 1995-09-15 Signal conditioned minimum error rate training for continuous speech recognition
PCT/US1996/014649 WO1997010587A1 (en) 1995-09-15 1996-09-12 Signal conditioned minimum error rate training for continuous speech recognition

Publications (1)

Publication Number Publication Date
DE69626954D1 true DE69626954D1 (de) 2003-04-30

Family

ID=24107331

Family Applications (1)

Application Number Title Priority Date Filing Date
DE69626954T Expired - Lifetime DE69626954D1 (de) 1995-09-15 1996-09-12 Signalkonditioniertes training mit minimaler fehlerrate für kontinuierliche spracherkennung

Country Status (5)

Country Link
US (1) US5806029A (de)
EP (1) EP0792503B1 (de)
CA (1) CA2204866C (de)
DE (1) DE69626954D1 (de)
WO (1) WO1997010587A1 (de)

Families Citing this family (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2748342B1 (fr) * 1996-05-06 1998-07-17 France Telecom Procede et dispositif de filtrage par egalisation d'un signal de parole, mettant en oeuvre un modele statistique de ce signal
SE9602622L (sv) * 1996-07-01 1997-09-08 Telia Ab Förfarande och arrangemang för adaptering av modeller vid exempelvis talarverifieringssystem
JPH1063293A (ja) * 1996-08-23 1998-03-06 Kokusai Denshin Denwa Co Ltd <Kdd> 電話音声認識装置
KR19990087167A (ko) * 1996-12-24 1999-12-15 롤페스 요하네스 게라투스 알베르투스 음성 인식 시스템 훈련 방법 및 그 방법을실행하는 장치,특히, 휴대용 전화 장치
US6076057A (en) * 1997-05-21 2000-06-13 At&T Corp Unsupervised HMM adaptation based on speech-silence discrimination
US5960397A (en) * 1997-05-27 1999-09-28 At&T Corp System and method of recognizing an acoustic environment to adapt a set of based recognition models to the current acoustic environment for subsequent speech recognition
KR100450787B1 (ko) * 1997-06-18 2005-05-03 삼성전자주식회사 스펙트럼의동적영역정규화에의한음성특징추출장치및방법
US6343267B1 (en) 1998-04-30 2002-01-29 Matsushita Electric Industrial Co., Ltd. Dimensionality reduction for speaker normalization and speaker and environment adaptation using eigenvoice techniques
US6263309B1 (en) 1998-04-30 2001-07-17 Matsushita Electric Industrial Co., Ltd. Maximum likelihood method for finding an adapted speaker model in eigenvoice space
US6076053A (en) * 1998-05-21 2000-06-13 Lucent Technologies Inc. Methods and apparatus for discriminative training and adaptation of pronunciation networks
US6253179B1 (en) * 1999-01-29 2001-06-26 International Business Machines Corporation Method and apparatus for multi-environment speaker verification
US6574596B2 (en) * 1999-02-08 2003-06-03 Qualcomm Incorporated Voice recognition rejection scheme
US6711541B1 (en) 1999-09-07 2004-03-23 Matsushita Electric Industrial Co., Ltd. Technique for developing discriminative sound units for speech recognition and allophone modeling
KR100307623B1 (ko) * 1999-10-21 2001-11-02 윤종용 엠.에이.피 화자 적응 조건에서 파라미터의 분별적 추정 방법 및 장치 및 이를 각각 포함한 음성 인식 방법 및 장치
US6571208B1 (en) 1999-11-29 2003-05-27 Matsushita Electric Industrial Co., Ltd. Context-dependent acoustic models for medium and large vocabulary speech recognition with eigenvoice training
US6526379B1 (en) 1999-11-29 2003-02-25 Matsushita Electric Industrial Co., Ltd. Discriminative clustering methods for automatic speech recognition
US7219056B2 (en) * 2000-04-20 2007-05-15 International Business Machines Corporation Determining and using acoustic confusability, acoustic perplexity and synthetic acoustic word error rate
JP4590692B2 (ja) * 2000-06-28 2010-12-01 パナソニック株式会社 音響モデル作成装置及びその方法
US6728674B1 (en) 2000-07-31 2004-04-27 Intel Corporation Method and system for training of a classifier
US7451085B2 (en) * 2000-10-13 2008-11-11 At&T Intellectual Property Ii, L.P. System and method for providing a compensated speech recognition model for speech recognition
US6985858B2 (en) * 2001-03-20 2006-01-10 Microsoft Corporation Method and apparatus for removing noise from feature vectors
US7437289B2 (en) * 2001-08-16 2008-10-14 International Business Machines Corporation Methods and apparatus for the systematic adaptation of classification systems from sparse adaptation data
FR2848715B1 (fr) * 2002-12-11 2005-02-18 France Telecom Procede et systeme de correction multi-references des deformations spectrales de la voix introduites par un reseau de communication
US7617104B2 (en) * 2003-01-21 2009-11-10 Microsoft Corporation Method of speech recognition using hidden trajectory Hidden Markov Models
US7499857B2 (en) * 2003-05-15 2009-03-03 Microsoft Corporation Adaptation of compressed acoustic models
US7318062B2 (en) * 2004-02-05 2008-01-08 Intel Corporation Storing method metadata in code
US7509259B2 (en) * 2004-12-21 2009-03-24 Motorola, Inc. Method of refining statistical pattern recognition models and statistical pattern recognizers
WO2006087040A1 (en) * 2005-02-17 2006-08-24 Loquendo S.P.A. Method and system for automatically providing linguistic formulations that are outside a recognition domain of an automatic speech recognition system
US20060235698A1 (en) * 2005-04-13 2006-10-19 Cane David A Apparatus for controlling a home theater system by speech commands
US7814040B1 (en) 2006-01-31 2010-10-12 The Research Foundation Of State University Of New York System and method for image annotation and multi-modal image retrieval using probabilistic semantic models
CN101154379B (zh) * 2006-09-27 2011-11-23 夏普株式会社 定位语音中的关键词的方法和设备以及语音识别系统
WO2008096582A1 (ja) * 2007-02-06 2008-08-14 Nec Corporation 認識器重み学習装置および音声認識装置、ならびに、システム
WO2009038822A2 (en) * 2007-05-25 2009-03-26 The Research Foundation Of State University Of New York Spectral clustering for multi-type relational data
US8275615B2 (en) * 2007-07-13 2012-09-25 International Business Machines Corporation Model weighting, selection and hypotheses combination for automatic speech recognition and machine translation
US20100023315A1 (en) * 2008-07-25 2010-01-28 Microsoft Corporation Random walk restarts in minimum error rate training
US10447315B2 (en) * 2016-08-15 2019-10-15 Seagate Technologies Llc Channel error rate optimization using Markov codes

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4348553A (en) * 1980-07-02 1982-09-07 International Business Machines Corporation Parallel pattern verifier with dynamic time warping
US4718093A (en) * 1984-03-27 1988-01-05 Exxon Research And Engineering Company Speech recognition method including biased principal components
US4783804A (en) * 1985-03-21 1988-11-08 American Telephone And Telegraph Company, At&T Bell Laboratories Hidden Markov model speech recognition arrangement
US4926488A (en) * 1987-07-09 1990-05-15 International Business Machines Corporation Normalization of speech by adaptive labelling
US5148489A (en) * 1990-02-28 1992-09-15 Sri International Method for spectral estimation to improve noise robustness for speech recognition
US5125022A (en) * 1990-05-15 1992-06-23 Vcs Industries, Inc. Method for recognizing alphanumeric strings spoken over a telephone network
US5303299A (en) * 1990-05-15 1994-04-12 Vcs Industries, Inc. Method for continuous recognition of alphanumeric strings spoken over a telephone network
US5127043A (en) * 1990-05-15 1992-06-30 Vcs Industries, Inc. Simultaneous speaker-independent voice recognition and verification over a telephone network
US5222146A (en) * 1991-10-23 1993-06-22 International Business Machines Corporation Speech recognition apparatus having a speech coder outputting acoustic prototype ranks
US5349645A (en) * 1991-12-31 1994-09-20 Matsushita Electric Industrial Co., Ltd. Word hypothesizer for continuous speech decoding using stressed-vowel centered bidirectional tree searches
DE69322894T2 (de) * 1992-03-02 1999-07-29 At & T Corp., New York, N.Y. Lernverfahren und Gerät zur Spracherkennung
US5590242A (en) * 1994-03-24 1996-12-31 Lucent Technologies Inc. Signal bias removal for robust telephone speech recognition

Also Published As

Publication number Publication date
EP0792503A4 (de) 1999-07-14
EP0792503B1 (de) 2003-03-26
CA2204866A1 (en) 1997-03-20
EP0792503A1 (de) 1997-09-03
WO1997010587A1 (en) 1997-03-20
US5806029A (en) 1998-09-08
CA2204866C (en) 2002-01-22

Similar Documents

Publication Publication Date Title
DE69626954D1 (de) Signalkonditioniertes training mit minimaler fehlerrate für kontinuierliche spracherkennung
DE69615667D1 (de) Spracherkennung
DE69432570D1 (de) Spracherkennung
EP0680033A3 (de) Veränderung der Sprechgeschwindigkeit für auf linearer Prädiktion basierende Analyse-durch-Synthese Sprachkodierer.
DE69514382D1 (de) Spracherkennung
NL1002387A1 (nl) Elektrodepositie-apparaat.
DE69613910D1 (de) Adaptives, auf der Grundlage eines Kodebuchs arbeitendes Sprachkompressionssystem
FI954573A (fi) Asiayhteydessä olevan puheen tunnistus
DE69615832D1 (de) Sprachsynthese mit wellenformen
DE69434568D1 (de) Mikrofonsystem für telekonferenzsystem
DE69819951D1 (de) Spracherkenner mit Rauschadaptierung
DK0749109T3 (da) Talegenkendelse for tonesprog
DE69633893D1 (de) Trellisumwandler für Trellisdekoder
DE69600999D1 (de) Tankentlüftungsdurchflussregler
DE69524321D1 (de) Spracherkenner
DE19680199D2 (de) Taucherschlitten
DE69624450D1 (de) Katheter mit verbesserter Mehrzweckkrümmung
DE69609531D1 (de) Sprachanpassungsgerät
DE69627517D1 (de) Adaptiver regler zum spritzgiessen
DE69331247D1 (de) Spracherkennungssystem
ITMI950050A0 (it) Erogatore per autorestiratori subacquei.
DE69425591D1 (de) Trainingsverfahren für einen Spracherkenner
EP0660304A3 (de) Training eines Spracherkennungssystems unter Verwendung von Biosignalen.
NL194481B (nl) Spraaksynthese-inrichting.
DE69621674D1 (de) Trainingssystem für Referenzmuster und dieses Trainingssystem benutzendes Spracherkennungssystem

Legal Events

Date Code Title Description
8332 No legal effect for de