ES2158702T3 - Procedimiento para determinar la probabilidad de la aparicion de una secuencia de al menos dos palabras durante un reconocimiento de voz. - Google Patents

Procedimiento para determinar la probabilidad de la aparicion de una secuencia de al menos dos palabras durante un reconocimiento de voz.

Info

Publication number
ES2158702T3
ES2158702T3 ES98954131T ES98954131T ES2158702T3 ES 2158702 T3 ES2158702 T3 ES 2158702T3 ES 98954131 T ES98954131 T ES 98954131T ES 98954131 T ES98954131 T ES 98954131T ES 2158702 T3 ES2158702 T3 ES 2158702T3
Authority
ES
Spain
Prior art keywords
designates
linguistic
probability
sequence
classes
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
ES98954131T
Other languages
English (en)
Inventor
Petra Witschel
Harald Hoge
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.)
Siemens AG
Original Assignee
Siemens 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 Siemens AG filed Critical Siemens AG
Application granted granted Critical
Publication of ES2158702T3 publication Critical patent/ES2158702T3/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
    • G10L15/197—Probabilistic grammars, e.g. word 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (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)

Abstract

Procedimiento para determinar la probabilidad de la aparición de una secuencia de al menos dos palabras durante un reconocimiento de voz por medio de un ordenador, a) en el que un idioma presenta clases ling¿ uísticas: (C1,..., Ck) = F((f1, v11,..., v1j)...(fm, vm1,...,vmj)), donde f1, ... fm designan una característica ling¿ uística, m designa el número de las características ling¿ uísticas, vm1 ... vmj designan los valores ling¿ uísticos de la característica ling¿ uística fm, j designa el número de los valores ling¿ uísticos, C1, ..., Ck designan las clases ling¿ uísticas, k designa el número de las clases ling¿ uísticas, F designa una especificación de representación (clasicador) de características ling¿ uísticas y de valores ling¿ uísticos sobre clases ling¿ uísticas. b) en el que a una palabra se asigna al menos una de las clases ling¿ uísticas; c) en el que la probabilidad de la aparición de la secuencia de al menos dos palabras se determina por medio de: P(W) ¡ n i=1 P Ci P Ci-1 P(wijCi)xP(Ci j Ci-1)xP(Ci-1 j wi-1) donde P(W) designa la probabilidad de la aparición de la secuencia de al menos dos palabras W designa la secuencia de al menos dos palabras wi designa la palabra i de la secuencia W con (i = 1..n), n designa el número de las palabras wi de la secuencia W, Ci designa una clase ling¿ uística C, que pertenece a una palabra wi, Ci-1 designa una clase ling¿ uística, que pertenece a una palabra wi-1, Ci designa la suma de todas las clases ling¿ uísticas C, que pertenecen una palabra wi, P(wijCi) designa la probabilidad condicionada de la palabra, P(Ci j Ci-1) designa la probabilidad de bigramas (también: bigramas de clases probabilidad de bigramas) P(Ci-1 j wi-1) designa la probabilidad condicionada de las clases.
ES98954131T 1997-09-17 1998-09-07 Procedimiento para determinar la probabilidad de la aparicion de una secuencia de al menos dos palabras durante un reconocimiento de voz. Expired - Lifetime ES2158702T3 (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE19740911 1997-09-17

Publications (1)

Publication Number Publication Date
ES2158702T3 true ES2158702T3 (es) 2001-09-01

Family

ID=7842662

Family Applications (1)

Application Number Title Priority Date Filing Date
ES98954131T Expired - Lifetime ES2158702T3 (es) 1997-09-17 1998-09-07 Procedimiento para determinar la probabilidad de la aparicion de una secuencia de al menos dos palabras durante un reconocimiento de voz.

Country Status (6)

Country Link
EP (1) EP1016077B1 (es)
JP (1) JP4243017B2 (es)
CN (1) CN1111841C (es)
DE (1) DE59800737D1 (es)
ES (1) ES2158702T3 (es)
WO (1) WO1999014740A1 (es)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040078191A1 (en) * 2002-10-22 2004-04-22 Nokia Corporation Scalable neural network-based language identification from written text
EP1450350A1 (en) * 2003-02-20 2004-08-25 Sony International (Europe) GmbH Method for Recognizing Speech with attributes
US7197457B2 (en) * 2003-04-30 2007-03-27 Robert Bosch Gmbh Method for statistical language modeling in speech recognition
CA2486125C (en) 2003-10-30 2011-02-08 At&T Corp. A system and method of using meta-data in speech-processing
DE102004048348B4 (de) * 2004-10-01 2006-07-13 Daimlerchrysler Ag Verfahren zur Adaption und/oder Erzeugung statistischer Sprachmodelle
US8478589B2 (en) 2005-01-05 2013-07-02 At&T Intellectual Property Ii, L.P. Library of existing spoken dialog data for use in generating new natural language spoken dialog systems
US8185399B2 (en) 2005-01-05 2012-05-22 At&T Intellectual Property Ii, L.P. System and method of providing an automated data-collection in spoken dialog systems
US20060149553A1 (en) * 2005-01-05 2006-07-06 At&T Corp. System and method for using a library to interactively design natural language spoken dialog systems
JP4820240B2 (ja) * 2006-08-29 2011-11-24 日本放送協会 単語分類装置及び音声認識装置及び単語分類プログラム
CN101271450B (zh) * 2007-03-19 2010-09-29 株式会社东芝 裁剪语言模型的方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5418717A (en) * 1990-08-27 1995-05-23 Su; Keh-Yih Multiple score language processing system
DE69022237T2 (de) * 1990-10-16 1996-05-02 Ibm Sprachsyntheseeinrichtung nach dem phonetischen Hidden-Markov-Modell.
US5949961A (en) * 1995-07-19 1999-09-07 International Business Machines Corporation Word syllabification in speech synthesis system

Also Published As

Publication number Publication date
DE59800737D1 (de) 2001-06-21
EP1016077B1 (de) 2001-05-16
CN1270687A (zh) 2000-10-18
JP2001516903A (ja) 2001-10-02
EP1016077A1 (de) 2000-07-05
CN1111841C (zh) 2003-06-18
JP4243017B2 (ja) 2009-03-25
WO1999014740A1 (de) 1999-03-25

Similar Documents

Publication Publication Date Title
US5619410A (en) Keyword extraction apparatus for Japanese texts
Cutler et al. Explaining cross-linguistic differences in effects of lexical stress on spoken-word recognition
ES2158702T3 (es) Procedimiento para determinar la probabilidad de la aparicion de una secuencia de al menos dos palabras durante un reconocimiento de voz.
Thompson Pronouns and voice in Koyukon Athapaskan: A text-based study
Benites de Azevedo e Souza et al. Twistbytes-identification of cuneiform languages and german dialects at vardial 2019
Barasa Inflectional forms of tense and aspect in Ateso
McQueen et al. Words within words: Lexical statistics and lexical access
Zamsha The category of quantity in signs of Ukrainian Sign Language
Boukobza et al. Multi-word expression identification using sentence surface features
de Loupy et al. Word sense disambiguation using HMM tagger.
JPS56147269A (en) Electronic translator
JPS57127269A (en) Character processing system
Barnes et al. Identifying Token-Level Dialectal Features in Social Media
Fontanella Componential analysis of personal affixes in Araucanian
Earl Part-of-speech implications of affixes.
Doerfer The Conditions for proving the genetic relationship of languages
Beasley " We Fall and Rise: Russian-Language Newspapers in New York City, 1889-1914" by Robert A. Karlowich (Book Review)
Kiss Towards a grammar of preposition-noun combinations
Burridge On the Trail of the Conestoga Modal: recent movements of modal auxiliaries in Pennsylvania German
Valera Hernández Many questions and few answers: on conversion in English
Perini The latest note on Lachmann's law
Kosch Discontinuous elements in Morphology
Black et al. Trigger-pair predictors in parsing and tagging
Lee Non-focus verbs in Maguindanao
Fofliger Oblique Pronoun Remnants on Comparative Prepositions in West Semitic1

Legal Events

Date Code Title Description
FG2A Definitive protection

Ref document number: 1016077

Country of ref document: ES