DE60134395D1 - Diskriminatives Trainieren von Hidden Markov Modellen für die Erkennung fliessender Sprache - Google Patents

Diskriminatives Trainieren von Hidden Markov Modellen für die Erkennung fliessender Sprache

Info

Publication number
DE60134395D1
DE60134395D1 DE60134395T DE60134395T DE60134395D1 DE 60134395 D1 DE60134395 D1 DE 60134395D1 DE 60134395 T DE60134395 T DE 60134395T DE 60134395 T DE60134395 T DE 60134395T DE 60134395 D1 DE60134395 D1 DE 60134395D1
Authority
DE
Germany
Prior art keywords
segment
correct
incorrect
state sequence
recognition
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
DE60134395T
Other languages
English (en)
Inventor
Girija Yegnanarayanan
Vladimir Sejnoha
Ramesh Sarukkai
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.)
Lernout and Hauspie Speech Products NV
Original Assignee
Lernout and Hauspie Speech Products NV
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 Lernout and Hauspie Speech Products NV filed Critical Lernout and Hauspie Speech Products NV
Application granted granted Critical
Publication of DE60134395D1 publication Critical patent/DE60134395D1/de
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
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]
    • G10L15/144—Training of HMMs
    • G10L15/146—Training of HMMs with insufficient amount of training data, e.g. state sharing, tying, deleted interpolation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Probability & Statistics with Applications (AREA)
  • Machine Translation (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)
  • Document Processing Apparatus (AREA)
  • Pens And Brushes (AREA)
  • Display Devices Of Pinball Game Machines (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measuring Temperature Or Quantity Of Heat (AREA)
  • Electrophonic Musical Instruments (AREA)
DE60134395T 2000-04-05 2001-04-03 Diskriminatives Trainieren von Hidden Markov Modellen für die Erkennung fliessender Sprache Expired - Lifetime DE60134395D1 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US09/543,202 US6490555B1 (en) 1997-03-14 2000-04-05 Discriminatively trained mixture models in continuous speech recognition
PCT/IB2001/000726 WO2001075862A2 (en) 2000-04-05 2001-04-03 Discriminatively trained mixture models in continuous speech recognition

Publications (1)

Publication Number Publication Date
DE60134395D1 true DE60134395D1 (de) 2008-07-24

Family

ID=24167006

Family Applications (1)

Application Number Title Priority Date Filing Date
DE60134395T Expired - Lifetime DE60134395D1 (de) 2000-04-05 2001-04-03 Diskriminatives Trainieren von Hidden Markov Modellen für die Erkennung fliessender Sprache

Country Status (7)

Country Link
US (1) US6490555B1 (de)
EP (1) EP1269464B1 (de)
JP (1) JP5134751B2 (de)
AT (1) ATE398323T1 (de)
AU (1) AU2001250579A1 (de)
DE (1) DE60134395D1 (de)
WO (1) WO2001075862A2 (de)

Families Citing this family (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7020845B1 (en) * 1999-11-15 2006-03-28 Gottfurcht Elliot A Navigating internet content on a television using a simplified interface and a remote control
US7003455B1 (en) * 2000-10-16 2006-02-21 Microsoft Corporation Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech
DE10120513C1 (de) 2001-04-26 2003-01-09 Siemens Ag Verfahren zur Bestimmung einer Folge von Lautbausteinen zum Synthetisieren eines Sprachsignals einer tonalen Sprache
AUPR579601A0 (en) * 2001-06-19 2001-07-12 Syrinx Speech Systems Pty Limited On-line environmental and speaker model adaptation
US20040150676A1 (en) * 2002-03-25 2004-08-05 Gottfurcht Elliot A. Apparatus and method for simple wide-area network navigation
US7117148B2 (en) 2002-04-05 2006-10-03 Microsoft Corporation Method of noise reduction using correction vectors based on dynamic aspects of speech and noise normalization
FI121583B (fi) * 2002-07-05 2011-01-14 Syslore Oy Symbolijonon etsintä
US7752045B2 (en) 2002-10-07 2010-07-06 Carnegie Mellon University Systems and methods for comparing speech elements
EP1450350A1 (de) * 2003-02-20 2004-08-25 Sony International (Europe) GmbH Verfahren zur Spracherkennung mittels Attributen
US20040186714A1 (en) * 2003-03-18 2004-09-23 Aurilab, Llc Speech recognition improvement through post-processsing
US20040193412A1 (en) * 2003-03-18 2004-09-30 Aurilab, Llc Non-linear score scrunching for more efficient comparison of hypotheses
US8019602B2 (en) * 2004-01-20 2011-09-13 Microsoft Corporation Automatic speech recognition learning using user corrections
GB0420464D0 (en) * 2004-09-14 2004-10-20 Zentian Ltd A speech recognition circuit and method
EP1743897A1 (de) * 2005-07-15 2007-01-17 Gesellschaft für Biotechnologische Forschung mbH Aus Sorangium cellulosum erhältliche biologisch aktive Verbindungen
US20070083373A1 (en) * 2005-10-11 2007-04-12 Matsushita Electric Industrial Co., Ltd. Discriminative training of HMM models using maximum margin estimation for speech recognition
US8301449B2 (en) * 2006-10-16 2012-10-30 Microsoft Corporation Minimum classification error training with growth transformation optimization
US7885812B2 (en) * 2006-11-15 2011-02-08 Microsoft Corporation Joint training of feature extraction and acoustic model parameters for speech recognition
US20080147579A1 (en) * 2006-12-14 2008-06-19 Microsoft Corporation Discriminative training using boosted lasso
US7856351B2 (en) * 2007-01-19 2010-12-21 Microsoft Corporation Integrated speech recognition and semantic classification
US8423364B2 (en) * 2007-02-20 2013-04-16 Microsoft Corporation Generic framework for large-margin MCE training in speech recognition
JP5294086B2 (ja) * 2007-02-28 2013-09-18 日本電気株式会社 重み係数学習システム及び音声認識システム
US20080243503A1 (en) * 2007-03-30 2008-10-02 Microsoft Corporation Minimum divergence based discriminative training for pattern recognition
US8239332B2 (en) 2007-11-20 2012-08-07 Microsoft Corporation Constrained line search optimization for discriminative training of HMMS
US8843370B2 (en) * 2007-11-26 2014-09-23 Nuance Communications, Inc. Joint discriminative training of multiple speech recognizers
WO2009078256A1 (ja) * 2007-12-18 2009-06-25 Nec Corporation 発音変動規則抽出装置、発音変動規則抽出方法、および発音変動規則抽出用プログラム
US9240184B1 (en) * 2012-11-15 2016-01-19 Google Inc. Frame-level combination of deep neural network and gaussian mixture models
US9817881B2 (en) * 2013-10-16 2017-11-14 Cypress Semiconductor Corporation Hidden markov model processing engine
JP6461308B2 (ja) * 2015-04-16 2019-01-30 三菱電機株式会社 音声認識装置およびリスコアリング装置
CN111354344B (zh) * 2020-03-09 2023-08-22 第四范式（北京）技术有限公司 语音识别模型的训练方法、装置、电子设备及存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4741036A (en) 1985-01-31 1988-04-26 International Business Machines Corporation Determination of phone weights for markov models in a speech recognition system
US5027406A (en) * 1988-12-06 1991-06-25 Dragon Systems, Inc. Method for interactive speech recognition and training
US5388183A (en) 1991-09-30 1995-02-07 Kurzwell Applied Intelligence, Inc. Speech recognition providing multiple outputs
US5280563A (en) 1991-12-20 1994-01-18 Kurzweil Applied Intelligence, Inc. Method of optimizing a composite speech recognition expert
EP0559349B1 (de) 1992-03-02 1999-01-07 AT&T Corp. Lernverfahren und Gerät zur Spracherkennung
US5832430A (en) * 1994-12-29 1998-11-03 Lucent Technologies, Inc. Devices and methods for speech recognition of vocabulary words with simultaneous detection and verification
US5675706A (en) * 1995-03-31 1997-10-07 Lucent Technologies Inc. Vocabulary independent discriminative utterance verification for non-keyword rejection in subword based speech recognition
US5737489A (en) * 1995-09-15 1998-04-07 Lucent Technologies Inc. Discriminative utterance verification for connected digits recognition
US5895447A (en) * 1996-02-02 1999-04-20 International Business Machines Corporation Speech recognition using thresholded speaker class model selection or model adaptation
US5991720A (en) * 1996-05-06 1999-11-23 Matsushita Electric Industrial Co., Ltd. Speech recognition system employing multiple grammar networks
JPH10207485A (ja) * 1997-01-22 1998-08-07 Toshiba Corp 音声認識装置及び話者適応方法
US6122613A (en) * 1997-01-30 2000-09-19 Dragon Systems, Inc. Speech recognition using multiple recognizers (selectively) applied to the same input sample
US6292778B1 (en) * 1998-10-30 2001-09-18 Lucent Technologies Inc. Task-independent utterance verification with subword-based minimum verification error training
US7216079B1 (en) 1999-11-02 2007-05-08 Speechworks International, Inc. Method and apparatus for discriminative training of acoustic models of a speech recognition system

Also Published As

Publication number Publication date
EP1269464B1 (de) 2008-06-11
JP2004512544A (ja) 2004-04-22
US6490555B1 (en) 2002-12-03
ATE398323T1 (de) 2008-07-15
AU2001250579A1 (en) 2001-10-15
WO2001075862A2 (en) 2001-10-11
EP1269464A2 (de) 2003-01-02
WO2001075862A3 (en) 2002-01-10
JP5134751B2 (ja) 2013-01-30

Similar Documents

Publication Publication Date Title
DE60134395D1 (de) Diskriminatives Trainieren von Hidden Markov Modellen für die Erkennung fliessender Sprache
CN101645271B (zh) 发音质量评估系统中的置信度快速求取方法
Wang et al. Towards automatic assessment of spontaneous spoken English
CN105427858A (zh) 实现语音自动分类的方法及系统
CN104575490A (zh) 基于深度神经网络后验概率算法的口语发音评测方法
CN107871496B (zh) 语音识别方法和装置
ATE265083T1 (de) Verfahren und vorrichtung zum unterscheidenden training von akustischen modellen in einem spracherkennungssystem
CA2177638A1 (en) Utterance verification using word based minimum verification error training for recognizing a keyword string
WO2009025356A1 (ja) 音声認識装置および音声認識方法
TW200638337A (en) Using a spoken utterance for disambiguation of spelling inputs into a speech recognition system
Chen et al. Applying rhythm features to automatically assess non-native speech
CN105261246A (zh) 一种基于大数据挖掘技术的英语口语纠错系统
WO2007034478A3 (en) System and method for correcting speech
CN101650942A (zh) 基于韵律短语的韵律结构生成方法
EP1460615B1 (de) Sprachverarbeitungseinrichtung und -verfahren, aufzeichnungsmedium und programm
Gallwitz et al. Integrated recognition of words and prosodic phrase boundaries
Bernstein et al. Speech recognition by computer
DE69916297D1 (de) Zwischen-wörter verbindung phonemische modelle
Li et al. Improving mandarin tone mispronunciation detection for non-native learners with soft-target tone labels and blstm-based deep models
Zhao Study on the effectiveness of the asr-based english teaching software in helping college students’ listening learning
Uchat Hidden Markov Model and Speech Recognition
JPH08314490A (ja) ワードスポッティング型音声認識方法と装置
Hagen et al. Data driven subword unit modeling for speech recognition and its application to interactive reading tutors.
CN113053414B (zh) 一种发音评测方法及装置
Hernández-Mena et al. Creating a grammar-based speech recognition parser for Mexican Spanish using HTK, compatible with CMU Sphinx-III system

Legal Events

Date Code Title Description
8328 Change in the person/name/address of the agent

Representative=s name: PAE REINHARD, SKUHRA, WEISE & PARTNER GBR, 80801 M

8364 No opposition during term of opposition