ES2169572T3 - Procedimiento de reconocimiento de voz empleando una gramatica. - Google Patents

Procedimiento de reconocimiento de voz empleando una gramatica.

Info

Publication number
ES2169572T3
ES2169572T3 ES98965097T ES98965097T ES2169572T3 ES 2169572 T3 ES2169572 T3 ES 2169572T3 ES 98965097 T ES98965097 T ES 98965097T ES 98965097 T ES98965097 T ES 98965097T ES 2169572 T3 ES2169572 T3 ES 2169572T3
Authority
ES
Spain
Prior art keywords
voice recognition
grammar
recognition procedure
word sequence
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
ES98965097T
Other languages
English (en)
Inventor
Fritz Class
Ute Kilian
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.)
Mercedes Benz Group AG
Original Assignee
DaimlerChrysler AG
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 DaimlerChrysler AG filed Critical DaimlerChrysler AG
Application granted granted Critical
Publication of ES2169572T3 publication Critical patent/ES2169572T3/es
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
    • G10L15/18—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
    • G10L15/193—Formal grammars, e.g. finite state automata, context free grammars or word networks
    • 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
    • G10L15/187—Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
    • 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)
  • Artificial Intelligence (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)
  • Machine Translation (AREA)
  • Telephone Function (AREA)

Abstract

Procedimiento de reconocimiento de voz en secuencias de palabras compuestas de varias palabras de un vocabulario dado, en el que están previstos un primer procedimiento de reconocimiento y un segundo procedimiento de reconocimiento, en donde el primer procedimiento de reconocimiento y el segundo procedimiento de reconocimiento se aplican a segmentos separados de una secuencia de palabras a reconocer, caracterizado porque como primer procedimiento se aplica un procedimiento de reconocimiento de bigramas con sintaxis unívoca integrada, como segundo procedimiento de reconocimiento se aplica un procedimiento de reconocimiento con valoración estadística de las secuencias de palabras, y al efectuar un cambio del procedimiento de reconocimiento de bigramas con sintaxis unívoca integrada al segundo procedimiento de reconocimiento con valoración estadística de las secuencias de palabras se agrupan las dos últimas palabras del segmento tratado según el primer procedimiento para obtener una pseudopalabra que se trata con un procedimiento de reconocimiento de bigramas.
ES98965097T 1997-12-11 1998-12-02 Procedimiento de reconocimiento de voz empleando una gramatica. Expired - Lifetime ES2169572T3 (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE19754957A DE19754957A1 (de) 1997-12-11 1997-12-11 Verfahren zur Spracherkennung

Publications (1)

Publication Number Publication Date
ES2169572T3 true ES2169572T3 (es) 2002-07-01

Family

ID=7851483

Family Applications (1)

Application Number Title Priority Date Filing Date
ES98965097T Expired - Lifetime ES2169572T3 (es) 1997-12-11 1998-12-02 Procedimiento de reconocimiento de voz empleando una gramatica.

Country Status (7)

Country Link
US (1) US7020606B1 (es)
EP (1) EP1038293B1 (es)
JP (1) JP4360453B2 (es)
AT (1) ATE211291T1 (es)
DE (2) DE19754957A1 (es)
ES (1) ES2169572T3 (es)
WO (1) WO1999030314A1 (es)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102007042971A1 (de) * 2007-09-10 2009-03-12 Siemens Ag Spracherkennungsverfahren und Spracherkennungsvorrichtung
US20090245646A1 (en) * 2008-03-28 2009-10-01 Microsoft Corporation Online Handwriting Expression Recognition
US20100166314A1 (en) * 2008-12-30 2010-07-01 Microsoft Corporation Segment Sequence-Based Handwritten Expression Recognition
CN103971686B (zh) * 2013-01-30 2015-06-10 腾讯科技（深圳）有限公司 自动语音识别方法和系统
WO2014189399A1 (en) 2013-05-22 2014-11-27 Axon Doo A mixed-structure n-gram language model
LU101763B1 (en) * 2020-05-04 2021-11-05 Microsoft Technology Licensing Llc Microsegment secure speech transcription

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4718094A (en) * 1984-11-19 1988-01-05 International Business Machines Corp. Speech recognition system
DE3711348A1 (de) * 1987-04-03 1988-10-20 Philips Patentverwaltung Verfahren zum erkennen kontinuierlich gesprochener woerter
JPH01177600A (ja) * 1988-01-06 1989-07-13 Nec Corp 音声認識誤り訂正装置
JP3004023B2 (ja) * 1989-11-28 2000-01-31 株式会社東芝 音声認識装置
TW323364B (es) * 1993-11-24 1997-12-21 At & T Corp
DE19501599C1 (de) * 1995-01-20 1996-05-02 Daimler Benz Ag Verfahren zur Spracherkennung
JP3180655B2 (ja) * 1995-06-19 2001-06-25 日本電信電話株式会社 パターンマッチングによる単語音声認識方法及びその方法を実施する装置
DE69517705T2 (de) * 1995-11-04 2000-11-23 International Business Machines Corp., Armonk Verfahren und vorrichtung zur anpassung der grösse eines sprachmodells in einem spracherkennungssystem
EP0849723A3 (en) * 1996-12-20 1998-12-30 ATR Interpreting Telecommunications Research Laboratories Speech recognition apparatus equipped with means for removing erroneous candidate of speech recognition
DE69937176T2 (de) * 1998-08-28 2008-07-10 International Business Machines Corp. Segmentierungsverfahren zur Erweiterung des aktiven Vokabulars von Spracherkennern

Also Published As

Publication number Publication date
WO1999030314A1 (de) 1999-06-17
JP2001526411A (ja) 2001-12-18
US7020606B1 (en) 2006-03-28
JP4360453B2 (ja) 2009-11-11
ATE211291T1 (de) 2002-01-15
EP1038293B1 (de) 2001-12-19
EP1038293A1 (de) 2000-09-27
DE59802584D1 (de) 2002-01-31
DE19754957A1 (de) 1999-06-17

Similar Documents

Publication Publication Date Title
DE60123952D1 (de) Erzeugung von einem einheitlichen aufgabeabhängigen sprachmodell mittels informationsauffindungverfahren
ATE314718T1 (de) Srecherangepasste spracherkennung
AU2002214658A1 (en) Speech recognition using word-in-phrase command
CA2270326A1 (en) A method of and a device for speech recognition employing neural network and markov model recognition techniques
ATE374421T1 (de) Segmentierungsverfahren zur erweiterung des aktiven vokabulars von spracherkennern
DE60128816D1 (de) Spracherkennungsverfahren mit ersetzungsbefehl
CA2162696A1 (en) Topic Discriminator
EP0801378A3 (en) Method and apparatus for speech recognition
CA2303362A1 (en) Speech reference enrollment method
CA2413658A1 (en) System and method of spoken language understanding in human computer dialogs
MX9505299A (es) Sistemas, metodos y articulos de fabricacion para realizar la hipotesizacion de n-cadenas optimas de alta resolucion.
FI20070933A7 (fi) Hajautettu äänentunnistusjärjestelmä
AU2002218916A1 (en) Hierarchical language models for speech recognition
ATE317583T1 (de) Texteditierung von erkannter sprache bei gleichzeitiger wiedergabe
TW200638337A (en) Using a spoken utterance for disambiguation of spelling inputs into a speech recognition system
BR9913524A (pt) Reconhecedor de voz, e, processo de reconhecimento de voz
DE60002584D1 (de) Anwendung von Referenzdaten für Spracherkennung
MXPA02005387A (es) Proceso y dispositivo para reconocimiento de voz que utiliza modelos de lenguaje desarticulados.
WO2003041051A3 (en) Hmm-based text-to-phoneme parser and method for training same
FR2769118B1 (fr) Procede de reconnaissance de parole
ATE232638T1 (de) Verfahren zur spracherkennung
SE9402284D0 (sv) Metod och anordning att adaptera en taligenkänningsutrustning för dialektala variationer i ett språk
ES2169572T3 (es) Procedimiento de reconocimiento de voz empleando una gramatica.
GB2196460B (en) Methods for comparing an input voice pattern with a registered voice pattern and voice recognition systems
FI942518L (fi) HMM-malliin perustuva puheentunnistusmenetelmä

Legal Events

Date Code Title Description
FG2A Definitive protection

Ref document number: 1038293

Country of ref document: ES