CA2051602A1 - Methode et appareil de generation de modeles de paroles n'utilisant qu'un petit nombre d'emissions vocales - Google Patents

Methode et appareil de generation de modeles de paroles n'utilisant qu'un petit nombre d'emissions vocales

Info

Publication number
CA2051602A1
CA2051602A1 CA2051602A CA2051602A CA2051602A1 CA 2051602 A1 CA2051602 A1 CA 2051602A1 CA 2051602 A CA2051602 A CA 2051602A CA 2051602 A CA2051602 A CA 2051602A CA 2051602 A1 CA2051602 A1 CA 2051602A1
Authority
CA
Canada
Prior art keywords
word
match
match score
utterances
models
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
CA2051602A
Other languages
English (en)
Other versions
CA2051602C (fr
Inventor
Peter Fitzhugh Brown
Steven V. De Gennaro
Peter Vincent De Souza
Mark E. Epstein
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.)
International Business Machines Corp
Original Assignee
International Business Machines 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 International Business Machines Corp filed Critical International Business Machines Corp
Publication of CA2051602A1 publication Critical patent/CA2051602A1/fr
Application granted granted Critical
Publication of CA2051602C publication Critical patent/CA2051602C/fr
Anticipated expiration legal-status Critical
Expired - Fee Related 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
    • G10L15/08—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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Probability & Statistics with Applications (AREA)
  • Machine Translation (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
CA002051602A 1990-10-23 1991-09-17 Methode et appareil de generation de modeles de paroles n'utilisant qu'un petit nombre d'emissions vocales Expired - Fee Related CA2051602C (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US07/602,020 US5293451A (en) 1990-10-23 1990-10-23 Method and apparatus for generating models of spoken words based on a small number of utterances
US07/602,020 1990-10-23

Publications (2)

Publication Number Publication Date
CA2051602A1 true CA2051602A1 (fr) 1992-04-24
CA2051602C CA2051602C (fr) 1996-03-05

Family

ID=24409651

Family Applications (1)

Application Number Title Priority Date Filing Date
CA002051602A Expired - Fee Related CA2051602C (fr) 1990-10-23 1991-09-17 Methode et appareil de generation de modeles de paroles n'utilisant qu'un petit nombre d'emissions vocales

Country Status (4)

Country Link
US (1) US5293451A (fr)
EP (1) EP0482395A3 (fr)
JP (1) JP2662112B2 (fr)
CA (1) CA2051602C (fr)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2570448B2 (ja) * 1989-12-28 1997-01-08 日本電気株式会社 標準パターン学習方法
US5915236A (en) * 1992-11-13 1999-06-22 Dragon Systems, Inc. Word recognition system which alters code executed as a function of available computational resources
CA2126380C (fr) * 1993-07-22 1998-07-07 Wu Chou Minimisation du taux d'erreur dans les modeles de chaine combines
US5497337A (en) * 1994-10-21 1996-03-05 International Business Machines Corporation Method for designing high-Q inductors in silicon technology without expensive metalization
DE19532114C2 (de) * 1995-08-31 2001-07-26 Deutsche Telekom Ag Sprachdialog-System zur automatisierten Ausgabe von Informationen
US6151575A (en) * 1996-10-28 2000-11-21 Dragon Systems, Inc. Rapid adaptation of speech models
US6092044A (en) * 1997-03-28 2000-07-18 Dragon Systems, Inc. Pronunciation generation in speech recognition
US6574597B1 (en) * 1998-05-08 2003-06-03 At&T Corp. Fully expanded context-dependent networks for speech recognition
NZ506981A (en) * 2000-09-15 2003-08-29 Univ Otago Computer based system for the recognition of speech characteristics using hidden markov method(s)
US8595004B2 (en) * 2007-12-18 2013-11-26 Nec Corporation Pronunciation variation rule extraction apparatus, pronunciation variation rule extraction method, and pronunciation variation rule extraction program
US8548807B2 (en) * 2009-06-09 2013-10-01 At&T Intellectual Property I, L.P. System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring
US8473293B1 (en) * 2012-04-17 2013-06-25 Google Inc. Dictionary filtering using market data
US9589564B2 (en) * 2014-02-05 2017-03-07 Google Inc. Multiple speech locale-specific hotword classifiers for selection of a speech locale

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4297528A (en) * 1979-09-10 1981-10-27 Interstate Electronics Corp. Training circuit for audio signal recognition computer
JPS59195299A (ja) * 1983-04-20 1984-11-06 富士通株式会社 特定話者音声認識装置
JPS59201100A (ja) * 1983-04-30 1984-11-14 富士通株式会社 音声標準パタン登録方法
JPS6024597A (ja) * 1983-07-21 1985-02-07 日本電気株式会社 音声登録方式
JPS6060697A (ja) * 1983-09-13 1985-04-08 富士通株式会社 音声標準特徴パタ−ン作成処理方式
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
US4759068A (en) * 1985-05-29 1988-07-19 International Business Machines Corporation Constructing Markov models of words from multiple utterances
US4903305A (en) * 1986-05-12 1990-02-20 Dragon Systems, Inc. Method for representing word models for use in speech recognition
US4837831A (en) * 1986-10-15 1989-06-06 Dragon Systems, Inc. Method for creating and using multiple-word sound models in speech recognition
US5146503A (en) * 1987-08-28 1992-09-08 British Telecommunications Public Limited Company Speech recognition

Also Published As

Publication number Publication date
US5293451A (en) 1994-03-08
EP0482395A2 (fr) 1992-04-29
JP2662112B2 (ja) 1997-10-08
JPH05143093A (ja) 1993-06-11
CA2051602C (fr) 1996-03-05
EP0482395A3 (en) 1993-08-04

Similar Documents

Publication Publication Date Title
Young et al. Tree-based state tying for high accuracy modelling
CA2163017A1 (fr) Methode de reconnaissance vocale utilisant une recherche a deux passages
Glavitsch et al. A system for retrieving speech documents
CA2126380A1 (fr) Minimisation du taux d'erreur dans les modeles de chaine combines
CA2091912A1 (fr) Systeme de reconnaissance vocale pour la traduction de langages naturels
CA2051602A1 (fr) Methode et appareil de generation de modeles de paroles n'utilisant qu'un petit nombre d'emissions vocales
WO1999018556A3 (fr) Apprentissage d'un modele de vocabulaire et/ou de langue
KR870009322A (ko) 스피커 배열 언어 인식 시스템
CA2117932A1 (fr) Reconnaissance vocale a decision ponderee
US20050187769A1 (en) Method and apparatus for constructing and using syllable-like unit language models
CA2162696A1 (fr) Identifieur de sujets de conversation
KR900018909A (ko) 언어 인식 방법 및 언어 인식기 트레이닝 방법
CA2089786A1 (fr) Appareil de reconnaissance de la parole contextuel utilisant une estimation du mot suivant
EP0376501A3 (fr) Dispositif pour la reconnaissance de la parole
CA2303362A1 (fr) Procede permettant de creer des references de signaux vocaux
CA2181205A1 (fr) Verification discriminative des paroles pour reconnaitre les suites de chiffres lies
EP0387602A3 (fr) Procédé et dispositif pour la détermination automatique des règles phonologiques pour un système de reconnaissance de la parole continue
EP0805434A3 (fr) Procédé et système de reconnaissance de la parole utilisant des modèles Markoviens cachés à densité de probabilités continue
CA2270326A1 (fr) Methode et dispositif de reconnaissance de la parole se servant d'un reseau neuronal et des techniques de reconnaissance du modele de markov
CA2180392A1 (fr) Criteres multiseuil selectionnables par l'utilisateur pour la reconnaissance vocale
EP0852374A3 (fr) Méthode et système de reconnaissance indépendante du locuteur de phrases dèfinies par un utilisateur
Antoniol et al. Language model representations for beam-search decoding
US7788096B2 (en) Method and apparatus for generating decision tree questions for speech processing
NO952049L (no) Talegjenkjenning, spesielt basert på Hidden Markov modeller (HMM)
Thorne A computer model for the perception of syntactic structure

Legal Events

Date Code Title Description
EEER Examination request
MKLA Lapsed