ATE487212T1 - Verstekte bedingte zufallfeldermodelle für phonetische klassifizierung und spracherkennung - Google Patents

Verstekte bedingte zufallfeldermodelle für phonetische klassifizierung und spracherkennung

Info

Publication number
ATE487212T1
ATE487212T1 AT05108905T AT05108905T ATE487212T1 AT E487212 T1 ATE487212 T1 AT E487212T1 AT 05108905 T AT05108905 T AT 05108905T AT 05108905 T AT05108905 T AT 05108905T AT E487212 T1 ATE487212 T1 AT E487212T1
Authority
AT
Austria
Prior art keywords
random field
conditional random
speech recognition
hidden conditional
field models
Prior art date
Application number
AT05108905T
Other languages
German (de)
English (en)
Inventor
Alejandro Acero
Asela J Gunawardana
Milind V Mahajan
Original Assignee
Microsoft 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 Microsoft Corp filed Critical Microsoft Corp
Application granted granted Critical
Publication of ATE487212T1 publication Critical patent/ATE487212T1/de

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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Machine Translation (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
  • Document Processing Apparatus (AREA)
AT05108905T 2004-10-15 2005-09-27 Verstekte bedingte zufallfeldermodelle für phonetische klassifizierung und spracherkennung ATE487212T1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US10/966,047 US7627473B2 (en) 2004-10-15 2004-10-15 Hidden conditional random field models for phonetic classification and speech recognition

Publications (1)

Publication Number Publication Date
ATE487212T1 true ATE487212T1 (de) 2010-11-15

Family

ID=35520793

Family Applications (1)

Application Number Title Priority Date Filing Date
AT05108905T ATE487212T1 (de) 2004-10-15 2005-09-27 Verstekte bedingte zufallfeldermodelle für phonetische klassifizierung und spracherkennung

Country Status (7)

Country Link
US (1) US7627473B2 (enExample)
EP (1) EP1647970B1 (enExample)
JP (1) JP5072206B2 (enExample)
KR (1) KR101153078B1 (enExample)
CN (1) CN1760974B (enExample)
AT (1) ATE487212T1 (enExample)
DE (1) DE602005024497D1 (enExample)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8751226B2 (en) 2006-06-29 2014-06-10 Nec Corporation Learning a verification model for speech recognition based on extracted recognition and language feature information
KR100774800B1 (ko) * 2006-09-06 2007-11-07 한국정보통신대학교 산학협력단 포아송 폴링 기법을 이용한 세그먼트 단위의 음성/비음성분류 방법 및 장치
WO2008105263A1 (ja) * 2007-02-28 2008-09-04 Nec Corporation 重み係数学習システム及び音声認識システム
US7509163B1 (en) * 2007-09-28 2009-03-24 International Business Machines Corporation Method and system for subject-adaptive real-time sleep stage classification
KR101230183B1 (ko) * 2008-07-14 2013-02-15 광운대학교 산학협력단 오디오 신호의 상태결정 장치
US20100076978A1 (en) * 2008-09-09 2010-03-25 Microsoft Corporation Summarizing online forums into question-context-answer triples
US8140328B2 (en) * 2008-12-01 2012-03-20 At&T Intellectual Property I, L.P. User intention based on N-best list of recognition hypotheses for utterances in a dialog
US8306806B2 (en) * 2008-12-02 2012-11-06 Microsoft Corporation Adaptive web mining of bilingual lexicon
US8473430B2 (en) * 2010-01-29 2013-06-25 Microsoft Corporation Deep-structured conditional random fields for sequential labeling and classification
US9355683B2 (en) 2010-07-30 2016-05-31 Samsung Electronics Co., Ltd. Audio playing method and apparatus
US9031844B2 (en) 2010-09-21 2015-05-12 Microsoft Technology Licensing, Llc Full-sequence training of deep structures for speech recognition
US9164983B2 (en) 2011-05-27 2015-10-20 Robert Bosch Gmbh Broad-coverage normalization system for social media language
CN104933048B (zh) * 2014-03-17 2018-08-31 联想(北京)有限公司 一种语音信息处理方法、装置和电子设备
US9785891B2 (en) * 2014-12-09 2017-10-10 Conduent Business Services, Llc Multi-task conditional random field models for sequence labeling
CN104700833A (zh) * 2014-12-29 2015-06-10 芜湖乐锐思信息咨询有限公司 一种大数据语音分类方法
US9875736B2 (en) 2015-02-19 2018-01-23 Microsoft Technology Licensing, Llc Pre-training and/or transfer learning for sequence taggers
US11030407B2 (en) * 2016-01-28 2021-06-08 Rakuten, Inc. Computer system, method and program for performing multilingual named entity recognition model transfer
US10311863B2 (en) * 2016-09-02 2019-06-04 Disney Enterprises, Inc. Classifying segments of speech based on acoustic features and context
CN109829164B (zh) * 2019-02-01 2020-05-22 北京字节跳动网络技术有限公司 用于生成文本的方法和装置
CN110826320B (zh) * 2019-11-28 2023-10-13 上海观安信息技术股份有限公司 一种基于文本识别的敏感数据发现方法及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3285047B2 (ja) * 1992-09-04 2002-05-27 日本電信電話株式会社 不特定話者用音声認識装置
JPH06266389A (ja) * 1993-03-10 1994-09-22 N T T Data Tsushin Kk 音素ラベリング装置
JPH0990975A (ja) * 1995-09-22 1997-04-04 Nippon Telegr & Teleph Corp <Ntt> パターン認識のためのモデル学習方法
US6505152B1 (en) * 1999-09-03 2003-01-07 Microsoft Corporation Method and apparatus for using formant models in speech systems

Also Published As

Publication number Publication date
EP1647970B1 (en) 2010-11-03
KR101153078B1 (ko) 2012-06-04
CN1760974B (zh) 2012-04-18
EP1647970A1 (en) 2006-04-19
KR20060050361A (ko) 2006-05-19
DE602005024497D1 (de) 2010-12-16
US20060085190A1 (en) 2006-04-20
JP2006113570A (ja) 2006-04-27
CN1760974A (zh) 2006-04-19
JP5072206B2 (ja) 2012-11-14
US7627473B2 (en) 2009-12-01

Similar Documents

Publication Publication Date Title
ATE487212T1 (de) Verstekte bedingte zufallfeldermodelle für phonetische klassifizierung und spracherkennung
ATE297588T1 (de) Anpassung des phonetischen kontextes zur verbesserung der spracherkennung
DE602005018552D1 (de) Verfahren zum anpassen eines neuronalen netzwerks einer automatischen spracherkennungseinrichtung
ATE417346T1 (de) Spracherkennungs- und korrektursystem, korrekturvorrichtung und verfahren zur erstellung eines lexikons von alternativen
WO2007056344A3 (en) Techiques for model optimization for statistical pattern recognition
EP1696421A3 (en) Learning in automatic speech recognition
WO2004100638A3 (en) Source-dependent text-to-speech system
ATE406073T1 (de) Verfahren zum nachtrainieren und betreiben eines hörgeräts und entsprechendes hörgerät
EP1705645A3 (en) Apparatus and method for analysis of language model changes
WO2008073850A3 (en) Method and apparatus for reading education
WO2009114499A3 (en) Methods and devices for language skill development
GB2443753A (en) Spoken language proficiency assessment by computer
DE602004030635D1 (de) Regelbasierte Grammatik für Slots und statistisches Modell für Preterminale in einem System zum Verstehen natürlicher Sprache
TW200601263A (en) Apparatus and method for synthesized audible response to an utterance in speaker-independent voice recognition
EP1575029A3 (en) Generating large units of graphonemes with mutual information criterion for letter to sound conversion
WO2011133766A3 (en) Methods and systems for training dictation-based speech-to-text systems using recorded samples
WO2009025356A1 (ja) 音声認識装置および音声認識方法
ATE335195T1 (de) Hintergrundlernen von sprecherstimmen
WO2015057907A3 (en) System and method for learning alternate pronunciations for speech recognition
WO2008087934A1 (ja) 拡張認識辞書学習装置と音声認識システム
ATE457510T1 (de) Spracherkennungssystem mit riesigem vokabular
ATE531031T1 (de) Segmentbasierte tonale modellierung für tonale sprachen
ATE401644T1 (de) Verfahren zur spracherkennung
FI20010792A7 (fi) Käyttäjäriippumattoman puheentunnistuksen järjestäminen
ATE445896T1 (de) Spracherkennungsverfahren das variationsinferenz mit veränderlichen zustandsraummodellen benuzt

Legal Events

Date Code Title Description
RER Ceased as to paragraph 5 lit. 3 law introducing patent treaties