MX9606483A - Metodo y sistema para realizar reconocimiento de habla. - Google Patents

Metodo y sistema para realizar reconocimiento de habla.

Info

Publication number
MX9606483A
MX9606483A MX9606483A MX9606483A MX9606483A MX 9606483 A MX9606483 A MX 9606483A MX 9606483 A MX9606483 A MX 9606483A MX 9606483 A MX9606483 A MX 9606483A MX 9606483 A MX9606483 A MX 9606483A
Authority
MX
Mexico
Prior art keywords
speech
speech recognition
speech signals
enhanced
signals
Prior art date
Application number
MX9606483A
Other languages
English (en)
Other versions
MXPA96006483A (es
Inventor
Mazin G Rahim
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 MX9606483A publication Critical patent/MX9606483A/es
Publication of MXPA96006483A publication Critical patent/MXPA96006483A/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
    • G10L15/02—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
    • G10L15/08—Speech classification or search
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • 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
    • G10L25/12—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 prediction coefficients
    • 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)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Telephonic Communication Services (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Telephone Function (AREA)
  • Character Discrimination (AREA)
  • Cable Transmission Systems, Equalization Of Radio And Reduction Of Echo (AREA)

Abstract

La presente invencion se refiere a procesamiento para reconocimiento de habla compensado para mejorar robustez de reconocimiento de habla en la presencia de señales de habla mejoradas. La compensacion supera los efectos adversos que puede tener la mejora de señal de habla en el desempeño de reconocimiento de habla, en donde la mejora de señal de habla provoca desajustes acusticos entre modelos de reconocimiento entrenados utilizando señales de habla no mejoradas y caracteriza a datos extraídos de las señales de habla mejoradas. Se proporciona compensacion en el extremo frontal de un sistema de reconocimiento de habla automático, al combinar codificacion predictiva lineal y análisis de parámetro cepstral basado en mel para calcular características cepstral de señales de habla transmitidas y utilizadas para procesamiento de reconocimiento de habla, por bancos de filtro mel ponderados selectivamente, cuando se procesan representaciones de dominio de frecuencia de las señales de habla mejoradas.
MXPA/A/1996/006483A 1995-12-20 1996-12-16 Metodo y sistema para realizar reconocimiento de habla MXPA96006483A (es)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/575,378 US5806022A (en) 1995-12-20 1995-12-20 Method and system for performing speech recognition
US08575378 1995-12-20

Publications (2)

Publication Number Publication Date
MX9606483A true MX9606483A (es) 1997-09-30
MXPA96006483A MXPA96006483A (es) 1998-07-03

Family

ID=

Also Published As

Publication number Publication date
DE69616724T2 (de) 2002-04-25
EP0780828A3 (en) 1998-12-30
CA2192397A1 (en) 1997-06-21
DE69635141T2 (de) 2006-03-09
EP0780828A2 (en) 1997-06-25
EP0780828B1 (en) 2001-11-07
EP1093112A3 (en) 2002-02-06
EP1093112A2 (en) 2001-04-18
JP4050350B2 (ja) 2008-02-20
DE69635141D1 (de) 2005-10-06
DE69616724D1 (de) 2001-12-13
EP1093112B1 (en) 2005-08-31
CA2192397C (en) 2001-04-03
JPH09179585A (ja) 1997-07-11
US5806022A (en) 1998-09-08

Similar Documents

Publication Publication Date Title
CA2192397A1 (en) Method and system for performing speech recognition
Talkin et al. A robust algorithm for pitch tracking (RAPT)
Zhu et al. On the use of variable frame rate analysis in speech recognition
US4811399A (en) Apparatus and method for automatic speech recognition
HK1030122A1 (en) Initiating a link between computers based on the decoding of an address steganographically embedded in an audio object
CN112397083A (zh) 语音处理方法及相关装置
KR20060044629A (ko) 신경 회로망을 이용한 음성 신호 분리 시스템 및 방법과음성 신호 강화 시스템
CN108597505A (zh) 语音识别方法、装置及终端设备
DE3275779D1 (en) Recognition of speech or speech-like sounds
AU2001277647A1 (en) Method for noise robust classification in speech coding
Haton Automatic speech recognition: A Review
Alam et al. Perceptual improvement of Wiener filtering employing a post-filter
Darling et al. Feature extraction in speech recognition using linear predictive coding: an overview
Kajita et al. Speech analysis and speech recognition using subbandautocorrelation analysis
KR100741355B1 (ko) 인지 가중 필터를 이용한 전처리 방법
Ortega-Garcia et al. Providing single and multi-channel acoustical robustness to speaker identification systems
Dionelis On single-channel speech enhancement and on non-linear modulation-domain Kalman filtering
KR20040073145A (ko) 음성인식기의 성능 향상 방법
Christiansen et al. Noise reduction in speech using adaptive filtering I: Signal processing algorithms
CN118379986B (zh) 基于关键词的非标准语音识别方法、装置、设备及介质
Nguyen et al. A technique for adapting to speech rate
KR100468817B1 (ko) 잡음 처리 기능을 갖춘 음성 인식 장치 및 음성 인식 방법
Ishizuka et al. Noise robust front-end processing with voice activity detection based on periodic to aperiodic component ratio.
KR100523905B1 (ko) 이중화된 검출조건을 이용한 음성 추출 방법
Soni The Comprehensive Analysis Speech Recognition System

Legal Events

Date Code Title Description
FA Abandonment or withdrawal