CA2024382A1 - Methode et dispositif pour trouver les meilleurs fractionnements dans les arbres de decision d'un modele de langage pour reconnaisseur de paroles - Google Patents

Methode et dispositif pour trouver les meilleurs fractionnements dans les arbres de decision d'un modele de langage pour reconnaisseur de paroles

Info

Publication number
CA2024382A1
CA2024382A1 CA2024382A CA2024382A CA2024382A1 CA 2024382 A1 CA2024382 A1 CA 2024382A1 CA 2024382 A CA2024382 A CA 2024382A CA 2024382 A CA2024382 A CA 2024382A CA 2024382 A1 CA2024382 A1 CA 2024382A1
Authority
CA
Canada
Prior art keywords
feature
predictor
values
value
sets
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
CA2024382A
Other languages
English (en)
Other versions
CA2024382C (fr
Inventor
Arthur Nadas
David Nahamoo
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 CA2024382A1 publication Critical patent/CA2024382A1/fr
Application granted granted Critical
Publication of CA2024382C publication Critical patent/CA2024382C/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
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
    • G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
    • G10L15/197—Probabilistic grammars, e.g. word n-grams

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
  • Machine Translation (AREA)
CA002024382A 1989-10-26 1990-08-31 Methode et dispositif pour trouver les meilleurs fractionnements dans les arbres de decision d'un modele de langage pour reconnaisseur de paroles Expired - Fee Related CA2024382C (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US427,420 1989-10-26
US07/427,420 US5263117A (en) 1989-10-26 1989-10-26 Method and apparatus for finding the best splits in a decision tree for a language model for a speech recognizer

Publications (2)

Publication Number Publication Date
CA2024382A1 true CA2024382A1 (fr) 1991-04-27
CA2024382C CA2024382C (fr) 1994-08-02

Family

ID=23694801

Family Applications (1)

Application Number Title Priority Date Filing Date
CA002024382A Expired - Fee Related CA2024382C (fr) 1989-10-26 1990-08-31 Methode et dispositif pour trouver les meilleurs fractionnements dans les arbres de decision d'un modele de langage pour reconnaisseur de paroles

Country Status (4)

Country Link
US (1) US5263117A (fr)
EP (1) EP0424665A2 (fr)
JP (1) JPH0756675B2 (fr)
CA (1) CA2024382C (fr)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5745649A (en) * 1994-07-07 1998-04-28 Nynex Science & Technology Corporation Automated speech recognition using a plurality of different multilayer perception structures to model a plurality of distinct phoneme categories
US5680509A (en) * 1994-09-27 1997-10-21 International Business Machines Corporation Method and apparatus for estimating phone class probabilities a-posteriori using a decision tree
US5729656A (en) * 1994-11-30 1998-03-17 International Business Machines Corporation Reduction of search space in speech recognition using phone boundaries and phone ranking
EP0838073B1 (fr) * 1995-05-26 2002-07-24 Speechworks International, Inc. Appareil et procede permettant une adaptation dynamique d'un systeme de reconnaissance vocale a vocabulaire tres etendu, tenant compte de contraintes imposees par une base de donnees de ce systeme
US5822730A (en) * 1996-08-22 1998-10-13 Dragon Systems, Inc. Lexical tree pre-filtering in speech recognition
US5864819A (en) * 1996-11-08 1999-01-26 International Business Machines Corporation Internal window object tree method for representing graphical user interface applications for speech navigation
US6167377A (en) * 1997-03-28 2000-12-26 Dragon Systems, Inc. Speech recognition language models
US6418431B1 (en) * 1998-03-30 2002-07-09 Microsoft Corporation Information retrieval and speech recognition based on language models
US6304773B1 (en) 1998-05-21 2001-10-16 Medtronic Physio-Control Manufacturing Corp. Automatic detection and reporting of cardiac asystole
US7031908B1 (en) 2000-06-01 2006-04-18 Microsoft Corporation Creating a language model for a language processing system
US6865528B1 (en) * 2000-06-01 2005-03-08 Microsoft Corporation Use of a unified language model
US6859774B2 (en) * 2001-05-02 2005-02-22 International Business Machines Corporation Error corrective mechanisms for consensus decoding of speech
US7711570B2 (en) * 2001-10-21 2010-05-04 Microsoft Corporation Application abstraction with dialog purpose
US8229753B2 (en) 2001-10-21 2012-07-24 Microsoft Corporation Web server controls for web enabled recognition and/or audible prompting
US7133856B2 (en) * 2002-05-17 2006-11-07 The Board Of Trustees Of The Leland Stanford Junior University Binary tree for complex supervised learning
US8301436B2 (en) * 2003-05-29 2012-10-30 Microsoft Corporation Semantic object synchronous understanding for highly interactive interface
US7200559B2 (en) 2003-05-29 2007-04-03 Microsoft Corporation Semantic object synchronous understanding implemented with speech application language tags
US7292982B1 (en) * 2003-05-29 2007-11-06 At&T Corp. Active labeling for spoken language understanding
US8160883B2 (en) 2004-01-10 2012-04-17 Microsoft Corporation Focus tracking in dialogs

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4181813A (en) * 1978-05-08 1980-01-01 John Marley System and method for speech recognition
JPS57211338A (en) * 1981-06-24 1982-12-25 Tokyo Shibaura Electric Co Tatal image diagnosis data treating apparatus
JPS58115497A (ja) * 1981-12-28 1983-07-09 シャープ株式会社 音声認識方法
US4658429A (en) * 1983-12-29 1987-04-14 Hitachi, Ltd. System and method for preparing a recognition dictionary
JPS60262290A (ja) * 1984-06-08 1985-12-25 Hitachi Ltd 情報認識システム
US4759068A (en) * 1985-05-29 1988-07-19 International Business Machines Corporation Constructing Markov models of words from multiple utterances
FR2591005B1 (fr) * 1985-12-04 1988-01-08 Thomson Csf Procede d'identification de structure arborescentes dans des images numeriques et son application a un dispositif de traitement d'images
US4719571A (en) * 1986-03-05 1988-01-12 International Business Machines Corporation Algorithm for constructing tree structured classifiers
US4852173A (en) * 1987-10-29 1989-07-25 International Business Machines Corporation Design and construction of a binary-tree system for language modelling

Also Published As

Publication number Publication date
EP0424665A3 (fr) 1994-01-12
CA2024382C (fr) 1994-08-02
EP0424665A2 (fr) 1991-05-02
JPH03147079A (ja) 1991-06-24
JPH0756675B2 (ja) 1995-06-14
US5263117A (en) 1993-11-16

Similar Documents

Publication Publication Date Title
CA2024382A1 (fr) Methode et dispositif pour trouver les meilleurs fractionnements dans les arbres de decision d'un modele de langage pour reconnaisseur de paroles
EP0313975A3 (en) Design and construction of a binary-tree system for language modelling
ES2012834A6 (es) Sistema y procedimiento para la calasificacion de informacion de difusion.
TW328629B (en) Production line analysis method and production line analysis device
CA2180392A1 (fr) Criteres multiseuil selectionnables par l'utilisateur pour la reconnaissance vocale
WO2000070426A8 (fr) Systeme permettant la gestion de charges
TW357313B (en) Methods and apparatus for handwriting recognition
CA2117932A1 (fr) Reconnaissance vocale a decision ponderee
AU7981794A (en) Method for unsupervised neural network classification with back propagation
GB0113659D0 (en) Provision of process related information
EP0847041A3 (fr) Procédé et dispositif de reconnaissance de la parole effectuant une adaptation au bruit
EP0734149A3 (fr) Procédé de traitement de données d'image
EP0825586A3 (fr) Préfiltrage par des arbres lexicaux pour la reconnaissance de la parole
TW338815B (en) Method and apparatus for character recognition of handwritten input
EP0361788A3 (fr) Système de reconnaissance de la parole
CA2235364A1 (fr) Regroupement automatise de syntagmes coherents
EP1610301A3 (fr) Procédé de reconnaissance de la parole basé sur une modélisation de la durée des mots
NZ502332A (en) A text classification system and method for the analysis and management of text
CA2493640A1 (fr) Perfectionnements apportes ou ayant trait a l'apport d'informations destine a des centres d'appels
CA2195927A1 (fr) Methode et systeme adaptatifs de resolution de problemes
ES2085428T3 (es) Un conjunto y un metodo para el tratamiento de compresion de datos por cuantificacion vectorial de busqueda en arbol binaria.
EP1073272A4 (fr) Procede de traitement de signal et dispositif de traitement video/audio
WO2004056409A3 (fr) Systeme et procede de selection de dispositif ou de composant d'interface de patient
EP0362840A3 (fr) Système de réseau neuronal
EP0762383A3 (fr) Dispositif d'adaptation de forme pour reconnaissance de la parole ou des formes

Legal Events

Date Code Title Description
EEER Examination request
MKLA Lapsed