ES2129596T3 - Procedimiento de reconocimiento de voz, con aprendizaje. - Google Patents

Procedimiento de reconocimiento de voz, con aprendizaje.

Info

Publication number
ES2129596T3
ES2129596T3 ES94400866T ES94400866T ES2129596T3 ES 2129596 T3 ES2129596 T3 ES 2129596T3 ES 94400866 T ES94400866 T ES 94400866T ES 94400866 T ES94400866 T ES 94400866T ES 2129596 T3 ES2129596 T3 ES 2129596T3
Authority
ES
Spain
Prior art keywords
learning
field
comes
voice recognition
signal
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
ES94400866T
Other languages
English (en)
Inventor
Philip Lockwood
Patrice Alexandre
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.)
Nortel Networks France SAS
Original Assignee
Matra Nortel Communications SAS
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 Matra Nortel Communications SAS filed Critical Matra Nortel Communications SAS
Application granted granted Critical
Publication of ES2129596T3 publication Critical patent/ES2129596T3/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
    • G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
    • 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
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band

Landscapes

  • Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Complex Calculations (AREA)
  • Character Discrimination (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Analysis (AREA)

Abstract

EN LA FASE DE RECONOCIMIENTO, SE TRATA LA SEÑAL QUE PROCEDE DE UN DETECTOR (10) PARA OBTENER PARAMETROS QUE SE COMPARAN CON LOS ALMACENADOS EN UN DICCIONARIO (16) EN LA FASE DE APRENDIZAJE PARA RECONOCER LAS ESTRUCTURAS VOCALES PRONUNCIADAS POR EL USUARIO EN UN MEDIOAMBIENTE RUIDOSO. LA OBTENCION DE DICHOS PARAMETROS DURANTE LAS FASES DE APRENDIZAJE Y DE RECONOCIMIENTO COMPRENDE LA FORMACION DE TRAMOS DIGITALES (S(N)) DE LONGITUD PREDETERMINADA A PARTIR DE LA SEÑAL QUE PROCEDE DEL DETECTOR, LA TRANSFORMACION EN EL CAMPO FRECUENCIAL PARA OBTENER UN ESPECTRO X(I), Y LA APLICACION DE UNA TRANSFORMACION INVERSA DEL CAMPO FRECUENCIAL AL CAMPO TEMPORAL A LA MAGNITUD EN QUE X(I) GAMMA, , DONDE X(II) REPRESENTA EL MODULO DEL ESPECTRO Y GAMMA REPRESENTA UN EXPONENTE APROPIADO.
ES94400866T 1993-04-23 1994-04-21 Procedimiento de reconocimiento de voz, con aprendizaje. Expired - Lifetime ES2129596T3 (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FR9304849A FR2704348B1 (fr) 1993-04-23 1993-04-23 Procede de reconnaissance de parole a apprentissage.

Publications (1)

Publication Number Publication Date
ES2129596T3 true ES2129596T3 (es) 1999-06-16

Family

ID=9446397

Family Applications (2)

Application Number Title Priority Date Filing Date
ES94400866T Expired - Lifetime ES2129596T3 (es) 1993-04-23 1994-04-21 Procedimiento de reconocimiento de voz, con aprendizaje.
ES97120086T Expired - Lifetime ES2150732T3 (es) 1993-04-23 1994-04-21 Procedimiento para el reconocimiento de palabras con fase de aprendizaje.

Family Applications After (1)

Application Number Title Priority Date Filing Date
ES97120086T Expired - Lifetime ES2150732T3 (es) 1993-04-23 1994-04-21 Procedimiento para el reconocimiento de palabras con fase de aprendizaje.

Country Status (8)

Country Link
US (1) US5692103A (es)
EP (2) EP0621582B1 (es)
JP (1) JPH07121197A (es)
DE (2) DE69416442T2 (es)
ES (2) ES2129596T3 (es)
FI (1) FI941874A (es)
FR (1) FR2704348B1 (es)
HK (1) HK1012459A1 (es)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6009385A (en) * 1994-12-15 1999-12-28 British Telecommunications Public Limited Company Speech processing
FI19992351A (fi) * 1999-10-29 2001-04-30 Nokia Mobile Phones Ltd Puheentunnistus
US6804640B1 (en) * 2000-02-29 2004-10-12 Nuance Communications Signal noise reduction using magnitude-domain spectral subtraction
GB0023498D0 (en) * 2000-09-26 2000-11-08 Domain Dynamics Ltd Spectral reconfiguration permutation and mapping
US7089184B2 (en) * 2001-03-22 2006-08-08 Nurv Center Technologies, Inc. Speech recognition for recognizing speaker-independent, continuous speech
DE102011003470A1 (de) 2011-02-01 2012-08-02 Sennheiser Electronic Gmbh & Co. Kg Headset und Hörer
TWI536366B (zh) * 2014-03-18 2016-06-01 財團法人工業技術研究院 新增口說語彙的語音辨識系統與方法及電腦可讀取媒體

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4937872A (en) * 1987-04-03 1990-06-26 American Telephone And Telegraph Company Neural computation by time concentration
JP2733955B2 (ja) * 1988-05-18 1998-03-30 日本電気株式会社 適応型音声認識装置
US5027406A (en) * 1988-12-06 1991-06-25 Dragon Systems, Inc. Method for interactive speech recognition and training
US5127055A (en) * 1988-12-30 1992-06-30 Kurzweil Applied Intelligence, Inc. Speech recognition apparatus & method having dynamic reference pattern adaptation
EP0435282B1 (en) * 1989-12-28 1997-04-23 Sharp Kabushiki Kaisha Voice recognition apparatus
US5440661A (en) * 1990-01-31 1995-08-08 The United States Of America As Represented By The United States Department Of Energy Time series association learning
US5345536A (en) * 1990-12-21 1994-09-06 Matsushita Electric Industrial Co., Ltd. Method of speech recognition
FR2681715B1 (fr) * 1991-09-25 1994-02-11 Matra Communication Procede de traitement de la parole en presence de bruits acoustiques: procede de soustraction spectrale non lineaire .

Also Published As

Publication number Publication date
DE69416442D1 (de) 1999-03-25
DE69425591D1 (de) 2000-09-21
US5692103A (en) 1997-11-25
FR2704348B1 (fr) 1995-07-07
FI941874A0 (fi) 1994-04-22
EP0621582A3 (fr) 1994-12-14
HK1012459A1 (en) 1999-07-30
EP0840290B1 (fr) 2000-08-16
DE69425591T2 (de) 2001-04-26
ES2150732T3 (es) 2000-12-01
JPH07121197A (ja) 1995-05-12
EP0621582A2 (fr) 1994-10-26
EP0621582B1 (fr) 1999-02-10
FR2704348A1 (fr) 1994-10-28
EP0840290A1 (fr) 1998-05-06
DE69416442T2 (de) 1999-10-21
FI941874A (fi) 1994-10-24

Similar Documents

Publication Publication Date Title
ES2129596T3 (es) Procedimiento de reconocimiento de voz, con aprendizaje.
BR9810297A (pt) Detecção de um sinal de propagação de espectro
FR2361078A1 (fr) Couche munie d'une attache de fixation extensible
SE9301596D0 (sv) Anordning foer att oeka talfoerstaaelsen vid oeversaetttning av tal fraan ett foersta spraak till ett andra spraak
EP1207518A3 (en) Speech recognition with dynamic programming
SE9902057D0 (sv) A Method of Improving the Intelligibility of a Sound Signal, and a Device for Reproducing a Sound Signal
FR2857798B1 (fr) Amplificateur de tension a faible consommation.
ES2128099T3 (es) Tratamiento de señales.
SE8900656D0 (sv) Timing generator
ES2169827T3 (es) Sistema de rectificacion criogenica con columna lateral para producir oxigeno de baja pureza y nitrogeno de alta pureza.
JPS5621231A (en) Audio synthesizer for kana character input
IT1270439B (it) Procedimento e dispositivo per la quantizzazione dei parametri spettrali in codificatori numerici della voce
MX9200835A (es) Aparato sin membrana generador de gas cloro.
JPS5880697A (ja) 音声認識方式
HUP9900570A2 (hu) Elszívó- és beáramoltatószerkezet úszómedencéhez
Dutton Sound Poetry
GB1444711A (en) Electronic visual aid for the deaf
SU563689A1 (ru) Устройство дл синтеза речи
ES2145356T3 (es) Oscilador controlado con tension.
JPS60246436A (ja) 音声出力装置
Monoi Communication Disorders in the Elderly From the Clinical Viewpoint
Fallona Corona spectroscopy.
KR880006599A (ko) 합성비디오 신호에 포함되어 있는 디지탈정보신호 분리 집적회로
KR950024145A (ko) 간략화된 음성인식방법
KR950005092U (ko) 음성 최대 출력 변환 회로

Legal Events

Date Code Title Description
FG2A Definitive protection

Ref document number: 621582

Country of ref document: ES