DE69519297D1 - Verfahren und vorrichtung zur spracherkennung mittels optimierter partieller buendelung von wahrscheinlichkeitsmischungen - Google Patents

Verfahren und vorrichtung zur spracherkennung mittels optimierter partieller buendelung von wahrscheinlichkeitsmischungen

Info

Publication number
DE69519297D1
DE69519297D1 DE69519297T DE69519297T DE69519297D1 DE 69519297 D1 DE69519297 D1 DE 69519297D1 DE 69519297 T DE69519297 T DE 69519297T DE 69519297 T DE69519297 T DE 69519297T DE 69519297 D1 DE69519297 D1 DE 69519297D1
Authority
DE
Germany
Prior art keywords
hmms
computationally
tied
likelihood
mixtures
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
DE69519297T
Other languages
English (en)
Other versions
DE69519297T2 (de
Inventor
Vassilios Digalakis
Hy Murveit
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.)
SRI International Inc
Original Assignee
SRI International Inc
Stanford Research Institute
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 SRI International Inc, Stanford Research Institute filed Critical SRI International Inc
Publication of DE69519297D1 publication Critical patent/DE69519297D1/de
Application granted granted Critical
Publication of DE69519297T2 publication Critical patent/DE69519297T2/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
    • G10L15/146—Training of HMMs with insufficient amount of training data, e.g. state sharing, tying, deleted interpolation

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)
  • Machine Translation (AREA)
  • Audible-Bandwidth Dynamoelectric Transducers Other Than Pickups (AREA)
  • Character Discrimination (AREA)
DE69519297T 1994-07-18 1995-07-13 Verfahren und vorrichtung zur spracherkennung mittels optimierter partieller buendelung von wahrscheinlichkeitsmischungen Expired - Lifetime DE69519297T2 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/276,742 US5825978A (en) 1994-07-18 1994-07-18 Method and apparatus for speech recognition using optimized partial mixture tying of HMM state functions
PCT/US1995/008816 WO1996002912A1 (en) 1994-07-18 1995-07-13 Method and apparatus for speech recognition using optimised partial probability mixture tying

Publications (2)

Publication Number Publication Date
DE69519297D1 true DE69519297D1 (de) 2000-12-07
DE69519297T2 DE69519297T2 (de) 2001-05-17

Family

ID=23057908

Family Applications (1)

Application Number Title Priority Date Filing Date
DE69519297T Expired - Lifetime DE69519297T2 (de) 1994-07-18 1995-07-13 Verfahren und vorrichtung zur spracherkennung mittels optimierter partieller buendelung von wahrscheinlichkeitsmischungen

Country Status (6)

Country Link
US (1) US5825978A (de)
EP (1) EP0771461B1 (de)
JP (2) JP4141495B2 (de)
AT (1) ATE197351T1 (de)
DE (1) DE69519297T2 (de)
WO (1) WO1996002912A1 (de)

Families Citing this family (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998014934A1 (en) * 1996-10-02 1998-04-09 Sri International Method and system for automatic text-independent grading of pronunciation for language instruction
US6009390A (en) * 1997-09-11 1999-12-28 Lucent Technologies Inc. Technique for selective use of Gaussian kernels and mixture component weights of tied-mixture hidden Markov models for speech recognition
US6807537B1 (en) * 1997-12-04 2004-10-19 Microsoft Corporation Mixtures of Bayesian networks
US5953701A (en) * 1998-01-22 1999-09-14 International Business Machines Corporation Speech recognition models combining gender-dependent and gender-independent phone states and using phonetic-context-dependence
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
EP0953971A1 (de) * 1998-05-01 1999-11-03 Entropic Cambridge Research Laboratory Ltd. System und Verfahren zur Spracherkennung
EP1084490B1 (de) * 1998-05-11 2003-03-26 Siemens Aktiengesellschaft Anordnung und verfahren zur erkennung eines vorgegebenen wortschatzes in gesprochener sprache durch einen rechner
US6725195B2 (en) * 1998-08-25 2004-04-20 Sri International Method and apparatus for probabilistic recognition using small number of state clusters
US6256607B1 (en) * 1998-09-08 2001-07-03 Sri International Method and apparatus for automatic recognition using features encoded with product-space vector quantization
US6260014B1 (en) * 1998-09-14 2001-07-10 International Business Machines Corporation Specific task composite acoustic models
US7702464B1 (en) 2001-08-21 2010-04-20 Maxygen, Inc. Method and apparatus for codon determining
US7873477B1 (en) 2001-08-21 2011-01-18 Codexis Mayflower Holdings, Llc Method and system using systematically varied data libraries
US8457903B1 (en) 1999-01-19 2013-06-04 Codexis Mayflower Holdings, Llc Method and/or apparatus for determining codons
US6246982B1 (en) * 1999-01-26 2001-06-12 International Business Machines Corporation Method for measuring distance between collections of distributions
US6195636B1 (en) * 1999-02-19 2001-02-27 Texas Instruments Incorporated Speech recognition over packet networks
US6526379B1 (en) 1999-11-29 2003-02-25 Matsushita Electric Industrial Co., Ltd. Discriminative clustering methods for automatic speech recognition
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
US7533020B2 (en) * 2001-09-28 2009-05-12 Nuance Communications, Inc. Method and apparatus for performing relational speech recognition
US7308404B2 (en) * 2001-09-28 2007-12-11 Sri International Method and apparatus for speech recognition using a dynamic vocabulary
US6996519B2 (en) * 2001-09-28 2006-02-07 Sri International Method and apparatus for performing relational speech recognition
US7236931B2 (en) * 2002-05-01 2007-06-26 Usb Ag, Stamford Branch Systems and methods for automatic acoustic speaker adaptation in computer-assisted transcription systems
JP3667332B2 (ja) * 2002-11-21 2005-07-06 松下電器産業株式会社 標準モデル作成装置及び標準モデル作成方法
DE10302101A1 (de) * 2003-01-21 2004-08-05 Infineon Technologies Ag Verfahren und Vorrichtung zum Trainieren eines Hidden Markov Modells, Computerprogramm-Element und Computerlesbares Speichermedium
CN1327406C (zh) * 2003-08-29 2007-07-18 摩托罗拉公司 开放式词汇表语音识别的方法
US7542949B2 (en) * 2004-05-12 2009-06-02 Mitsubishi Electric Research Laboratories, Inc. Determining temporal patterns in sensed data sequences by hierarchical decomposition of hidden Markov models
US7480617B2 (en) * 2004-09-21 2009-01-20 International Business Machines Corporation Method for likelihood computation in multi-stream HMM based speech recognition
US7970613B2 (en) 2005-11-12 2011-06-28 Sony Computer Entertainment Inc. Method and system for Gaussian probability data bit reduction and computation
US8010358B2 (en) * 2006-02-21 2011-08-30 Sony Computer Entertainment Inc. Voice recognition with parallel gender and age normalization
US7778831B2 (en) * 2006-02-21 2010-08-17 Sony Computer Entertainment Inc. Voice recognition with dynamic filter bank adjustment based on speaker categorization determined from runtime pitch
US20070233481A1 (en) * 2006-04-03 2007-10-04 Texas Instruments Inc. System and method for developing high accuracy acoustic models based on an implicit phone-set determination-based state-tying technique
US20070260459A1 (en) * 2006-05-04 2007-11-08 Texas Instruments, Incorporated System and method for generating heterogeneously tied gaussian mixture models for automatic speech recognition acoustic models
US8234116B2 (en) * 2006-08-22 2012-07-31 Microsoft Corporation Calculating cost measures between HMM acoustic models
US8176016B1 (en) * 2006-11-17 2012-05-08 At&T Intellectual Property Ii, L.P. Method and apparatus for rapid identification of column heterogeneity
US8229729B2 (en) * 2008-03-25 2012-07-24 International Business Machines Corporation Machine translation in continuous space
US8442833B2 (en) * 2009-02-17 2013-05-14 Sony Computer Entertainment Inc. Speech processing with source location estimation using signals from two or more microphones
US8788256B2 (en) 2009-02-17 2014-07-22 Sony Computer Entertainment Inc. Multiple language voice recognition
US8442829B2 (en) 2009-02-17 2013-05-14 Sony Computer Entertainment Inc. Automatic computation streaming partition for voice recognition on multiple processors with limited memory
US8515758B2 (en) 2010-04-14 2013-08-20 Microsoft Corporation Speech recognition including removal of irrelevant information
US8719023B2 (en) 2010-05-21 2014-05-06 Sony Computer Entertainment Inc. Robustness to environmental changes of a context dependent speech recognizer
US9153235B2 (en) 2012-04-09 2015-10-06 Sony Computer Entertainment Inc. Text dependent speaker recognition with long-term feature based on functional data analysis

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4587670A (en) * 1982-10-15 1986-05-06 At&T Bell Laboratories Hidden Markov model speech recognition arrangement
US4741036A (en) * 1985-01-31 1988-04-26 International Business Machines Corporation Determination of phone weights for markov models in a speech recognition system
US4783804A (en) * 1985-03-21 1988-11-08 American Telephone And Telegraph Company, At&T Bell Laboratories Hidden Markov model speech recognition arrangement
US4903305A (en) * 1986-05-12 1990-02-20 Dragon Systems, Inc. Method for representing word models for use in speech recognition
US4817156A (en) * 1987-08-10 1989-03-28 International Business Machines Corporation Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker
US5075896A (en) * 1989-10-25 1991-12-24 Xerox Corporation Character and phoneme recognition based on probability clustering
US5193142A (en) * 1990-11-15 1993-03-09 Matsushita Electric Industrial Co., Ltd. Training module for estimating mixture gaussian densities for speech-unit models in speech recognition systems
US5172228A (en) * 1991-11-19 1992-12-15 Utah State University Foundation Image compression method and apparatus employing distortion adaptive tree search vector quantization

Also Published As

Publication number Publication date
EP0771461A1 (de) 1997-05-07
WO1996002912A1 (en) 1996-02-01
DE69519297T2 (de) 2001-05-17
JP2007047818A (ja) 2007-02-22
EP0771461B1 (de) 2000-11-02
ATE197351T1 (de) 2000-11-15
JPH10505687A (ja) 1998-06-02
JP4141495B2 (ja) 2008-08-27
US5825978A (en) 1998-10-20

Similar Documents

Publication Publication Date Title
DE69519297D1 (de) Verfahren und vorrichtung zur spracherkennung mittels optimierter partieller buendelung von wahrscheinlichkeitsmischungen
Stolcke et al. Highly accurate phonetic segmentation using boundary correction models and system fusion
DE60309142D1 (de) Vorrichtung zur bestimmung von parametern eines gauss'schen mischungmodells (gmm) oder eines gmm basierten hidden markov modells
US5425129A (en) Method for word spotting in continuous speech
ATE134275T1 (de) Verfahren zur sprecheradaptiven erkennung von sprache
Gunawardana et al. Discriminative speaker adaptation with conditional maximum likelihood linear regression.
Livescu et al. Lexical modeling of non-native speech for automatic speech recognition
KR870009322A (ko) 스피커 배열 언어 인식 시스템
WO1996023298A3 (en) System amd method for generating and using context dependent sub-syllable models to recognize a tonal language
ATE345562T1 (de) Verfahren und vorrichtung zur erzeugung der referenzmuster für ein sprecherunabhängiges spracherkennungssystem
DE59904741D1 (de) Anordnung und verfahren zur erkennung eines vorgegebenen wortschatzes in gesprochener sprache durch einen rechner
Schwartz et al. Comparative experiments on large vocabulary speech recognition
Lamel et al. Continuous speech recognition at LIMSI
Lee et al. Acoustic modeling of subword units for speech recognition
Tian et al. Tone recognition with fractionized models and outlined features
Breslin et al. Integrated Online Speaker Clustering and Adaptation.
Odell et al. The CUHTK-Entropic 10xRT broadcast news transcription system
Finke et al. Flexible transcription alignment
AT&T
Le Floch et al. Investigations on speaker characterization from Orphee system techniques
Rogina et al. The Janus speech recognizer
CA2195445A1 (en) Method and apparatus for speech recognition using optimised partial probability mixture tying
Murveit et al. Training set issues in sri’s decipher speech recognition system
Nitta et al. One-model speech recognition and synthesis based on articulatory movement HMMs.
Wang et al. Context-dependent boundary model for refining boundaries segmentation of TTS units

Legal Events

Date Code Title Description
8364 No opposition during term of opposition