MX9505296A - Metodo y aparato para el reconocimiento de la voz, con reduccion del ruido de polarizacion. - Google Patents

Metodo y aparato para el reconocimiento de la voz, con reduccion del ruido de polarizacion.

Info

Publication number
MX9505296A
MX9505296A MX9505296A MX9505296A MX9505296A MX 9505296 A MX9505296 A MX 9505296A MX 9505296 A MX9505296 A MX 9505296A MX 9505296 A MX9505296 A MX 9505296A MX 9505296 A MX9505296 A MX 9505296A
Authority
MX
Mexico
Prior art keywords
vector
recognizer
speech
segmentation
feature
Prior art date
Application number
MX9505296A
Other languages
English (en)
Inventor
Biing-Hwang Juang
David Mansour
Jay Gordon Wilpon
Original Assignee
At & T 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 At & T Corp filed Critical At & T Corp
Publication of MX9505296A publication Critical patent/MX9505296A/es

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
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]
    • G10L15/144—Training of HMMs
    • 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
    • G10L15/04—Segmentation; Word boundary detection
    • 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
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • 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
    • G10L2015/0635—Training updating or merging of old and new templates; Mean values; Weighting

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)
  • Probability & Statistics with Applications (AREA)
  • Telephonic Communication Services (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

La presente invencion proporciona un reconocedor de voz que crea y actualiza el vector de compensacion conforme la voz de entrada es proporcionada al reconocedor. La presente invencion incluye un analizador de voz el cual transforma una señal de voz de entrada en una serie de vectores de característica o secuencia de observacion. Cada vector de característica es luego proporcionado a un reconocedor de voz, el cual modifica el vector de característica mediante la substraccion de un vector de compensacion previamente determinado, a partir de este. El reconocedor realiza luego la segmentacion y ajusta el vector de característica modificado a un vector modelo almacenado, el cual es definido como el vector de segmentacion. Posteriormente el reconocedor, de cuando en cuando, determina un vector de compensacion, siendo el nuevo vector de compensacion definido con base en la diferencia entre uno o más vectores de característica de entrada y sus respectivos vectores de segmentacion. El nuevo vector de compensacion puede ser luego usado ya sea para realizar otra iteracion de segmentacion más o la misma secuencia de observacion, o para realizar la segmentacion sobre vectores de características subsecuentes.
MX9505296A 1994-12-30 1995-12-14 Metodo y aparato para el reconocimiento de la voz, con reduccion del ruido de polarizacion. MX9505296A (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US08/366,657 US5812972A (en) 1994-12-30 1994-12-30 Adaptive decision directed speech recognition bias equalization method and apparatus

Publications (1)

Publication Number Publication Date
MX9505296A true MX9505296A (es) 1997-01-31

Family

ID=23443955

Family Applications (1)

Application Number Title Priority Date Filing Date
MX9505296A MX9505296A (es) 1994-12-30 1995-12-14 Metodo y aparato para el reconocimiento de la voz, con reduccion del ruido de polarizacion.

Country Status (5)

Country Link
US (1) US5812972A (es)
EP (1) EP0720149A1 (es)
JP (1) JPH08234788A (es)
CA (1) CA2165873A1 (es)
MX (1) MX9505296A (es)

Families Citing this family (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE69529223T2 (de) * 1994-08-18 2003-09-25 British Telecomm Testverfahren
JPH1063293A (ja) * 1996-08-23 1998-03-06 Kokusai Denshin Denwa Co Ltd <Kdd> 電話音声認識装置
DE19712632A1 (de) * 1997-03-26 1998-10-01 Thomson Brandt Gmbh Verfahren und Vorrichtung zur Sprachfernsteuerung von Geräten
FR2766604B1 (fr) * 1997-07-22 1999-10-01 France Telecom Procede et dispositif d'egalisation aveugle des effets d'un canal de transmission sur un signal de parole numerique
US6006182A (en) * 1997-09-22 1999-12-21 Northern Telecom Limited Speech recognition rejection method using generalized additive models
US6404876B1 (en) * 1997-09-25 2002-06-11 Gte Intelligent Network Services Incorporated System and method for voice activated dialing and routing under open access network control
US6173041B1 (en) * 1997-11-13 2001-01-09 Advanced Micro Devices, Inc. System and method for reducing call interruptions on a telephone
US6178230B1 (en) 1997-11-13 2001-01-23 Advanced Micro Devices, Inc. System and method for identifying a callee of an incoming telephone call
US6385303B1 (en) 1997-11-13 2002-05-07 Legerity, Inc. System and method for identifying and announcing a caller and a callee of an incoming telephone call
US6614885B2 (en) * 1998-08-14 2003-09-02 Intervoice Limited Partnership System and method for operating a highly distributed interactive voice response system
US6980952B1 (en) * 1998-08-15 2005-12-27 Texas Instruments Incorporated Source normalization training for HMM modeling of speech
TW418383B (en) * 1998-09-23 2001-01-11 Ind Tech Res Inst Telephone voice recognition system and method and the channel effect compensation device using the same
US6230129B1 (en) * 1998-11-25 2001-05-08 Matsushita Electric Industrial Co., Ltd. Segment-based similarity method for low complexity speech recognizer
DE19929462A1 (de) * 1999-06-26 2001-02-22 Philips Corp Intellectual Pty Verfahren zum Training eines automatischen Spracherkenners
US20010044719A1 (en) * 1999-07-02 2001-11-22 Mitsubishi Electric Research Laboratories, Inc. Method and system for recognizing, indexing, and searching acoustic signals
US6920421B2 (en) * 1999-12-28 2005-07-19 Sony Corporation Model adaptive apparatus for performing adaptation of a model used in pattern recognition considering recentness of a received pattern data
US6789062B1 (en) * 2000-02-25 2004-09-07 Speechworks International, Inc. Automatically retraining a speech recognition system
TW473704B (en) * 2000-08-30 2002-01-21 Ind Tech Res Inst Adaptive voice recognition method with noise compensation
US6959278B1 (en) * 2001-04-05 2005-10-25 Verizon Corporate Services Group Inc. Systems and methods for implementing segmentation in speech recognition systems
US6785648B2 (en) * 2001-05-31 2004-08-31 Sony Corporation System and method for performing speech recognition in cyclostationary noise environments
US6876728B2 (en) 2001-07-02 2005-04-05 Nortel Networks Limited Instant messaging using a wireless interface
US8644475B1 (en) 2001-10-16 2014-02-04 Rockstar Consortium Us Lp Telephony usage derived presence information
US20030135624A1 (en) * 2001-12-27 2003-07-17 Mckinnon Steve J. Dynamic presence management
DE10208468A1 (de) * 2002-02-27 2003-09-04 Bsh Bosch Siemens Hausgeraete Elektrisches Gerät, insbesondere Dunstabzugshaube
DE10208466A1 (de) * 2002-02-27 2004-01-29 BSH Bosch und Siemens Hausgeräte GmbH Elektrisches Haushaltsgerät
US20030225719A1 (en) * 2002-05-31 2003-12-04 Lucent Technologies, Inc. Methods and apparatus for fast and robust model training for object classification
US8392609B2 (en) 2002-09-17 2013-03-05 Apple Inc. Proximity detection for media proxies
US9118574B1 (en) 2003-11-26 2015-08-25 RPX Clearinghouse, LLC Presence reporting using wireless messaging
US7206389B1 (en) * 2004-01-07 2007-04-17 Nuance Communications, Inc. Method and apparatus for generating a speech-recognition-based call-routing system
JP4517163B2 (ja) * 2004-03-12 2010-08-04 株式会社国際電気通信基礎技術研究所 周波数特性等化装置
US10223934B2 (en) 2004-09-16 2019-03-05 Lena Foundation Systems and methods for expressive language, developmental disorder, and emotion assessment, and contextual feedback
US9355651B2 (en) 2004-09-16 2016-05-31 Lena Foundation System and method for expressive language, developmental disorder, and emotion assessment
US9240188B2 (en) 2004-09-16 2016-01-19 Lena Foundation System and method for expressive language, developmental disorder, and emotion assessment
US8938390B2 (en) * 2007-01-23 2015-01-20 Lena Foundation System and method for expressive language and developmental disorder assessment
CN101416237B (zh) * 2006-05-01 2012-05-30 日本电信电话株式会社 基于源和室内声学的概率模型的语音去混响方法和设备
US7725316B2 (en) * 2006-07-05 2010-05-25 General Motors Llc Applying speech recognition adaptation in an automated speech recognition system of a telematics-equipped vehicle
US7680657B2 (en) * 2006-08-15 2010-03-16 Microsoft Corporation Auto segmentation based partitioning and clustering approach to robust endpointing
WO2008091947A2 (en) 2007-01-23 2008-07-31 Infoture, Inc. System and method for detection and analysis of speech
US9118669B2 (en) 2010-09-30 2015-08-25 Alcatel Lucent Method and apparatus for voice signature authentication
US8965756B2 (en) * 2011-03-14 2015-02-24 Adobe Systems Incorporated Automatic equalization of coloration in speech recordings
DE102015102605A1 (de) * 2015-02-24 2016-08-25 Intel IP Corporation Verfahren und Vorrichtung zum Unterdrücken eines Fehlers einer Funkkanalsequenz
US10529357B2 (en) 2017-12-07 2020-01-07 Lena Foundation Systems and methods for automatic determination of infant cry and discrimination of cry from fussiness
US11270721B2 (en) * 2018-05-21 2022-03-08 Plantronics, Inc. Systems and methods of pre-processing of speech signals for improved speech recognition
CN113593534B (zh) * 2021-05-28 2023-07-14 思必驰科技股份有限公司 针对多口音语音识别的方法和装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
NL8500339A (nl) * 1985-02-07 1986-09-01 Philips Nv Adaptief responderend systeem.
JP2654942B2 (ja) * 1985-09-03 1997-09-17 モトロ−ラ・インコ−ポレ−テツド 音声通信装置及びその動作方法
JPH0833739B2 (ja) * 1990-09-13 1996-03-29 三菱電機株式会社 パターン表現モデル学習装置
WO1993001664A1 (en) * 1991-07-08 1993-01-21 Motorola, Inc. Remote voice control system
JPH05257492A (ja) * 1992-03-13 1993-10-08 Toshiba Corp 音声認識方式
US5440662A (en) * 1992-12-11 1995-08-08 At&T Corp. Keyword/non-keyword classification in isolated word speech recognition
US5483579A (en) * 1993-02-25 1996-01-09 Digital Acoustics, Inc. Voice recognition dialing system
US5664059A (en) * 1993-04-29 1997-09-02 Panasonic Technologies, Inc. Self-learning speaker adaptation based on spectral variation source decomposition

Also Published As

Publication number Publication date
CA2165873A1 (en) 1996-07-01
JPH08234788A (ja) 1996-09-13
US5812972A (en) 1998-09-22
EP0720149A1 (en) 1996-07-03

Similar Documents

Publication Publication Date Title
MX9505296A (es) Metodo y aparato para el reconocimiento de la voz, con reduccion del ruido de polarizacion.
US5806029A (en) Signal conditioned minimum error rate training for continuous speech recognition
EP1195744B1 (en) Noise robust voice recognition
EP0831456A3 (en) Speech recognition method and apparatus therefor
MX9505299A (es) Sistemas, metodos y articulos de fabricacion para realizar la hipotesizacion de n-cadenas optimas de alta resolucion.
EP0674306A2 (en) Signal bias removal for robust telephone speech recognition
HK1062738A1 (en) Apparation and method for performing voice recognition using acoustic feature vector modification
JPS5525150A (en) Pattern recognition unit
EP1083541A3 (en) A method and apparatus for speech detection
JPS5722295A (en) Speaker recognizing system
WO1997010587A9 (en) Signal conditioned minimum error rate training for continuous speech recognition
FR2274101B1 (es)
ATE345562T1 (de) Verfahren und vorrichtung zur erzeugung der referenzmuster für ein sprecherunabhängiges spracherkennungssystem
US5963904A (en) Phoneme dividing method using multilevel neural network
SG140445A1 (en) Method and apparatus for automatically recognizing audio data
EP0806761A3 (en) Improvements in or relating to speech processing
Hansen Adaptive source generator compensation and enhancement for speech recognition in noisy stressful environments
DE3279549D1 (en) Apparatus and method for articulatory speech recognition
Wrench A realtime implementation of a text independent speaker recognition system
Binh et al. A high-performance speech-recognition method based on a nonlinear neural network
JPH04267300A (ja) 雑音除去と話者適応の機能を有する音声認識装置
Shimamura et al. Adaptive nonlinear prediction based on order statistics for speech signals
JPH04181298A (ja) 参照ベクトル更新方法
KR100346736B1 (ko) 음성인식방법
EP0428449A3 (en) Method and apparatus for pattern recognition, especially for speaker-independent speech recognition