ATE450031T1 - Verfahren zur spracherkennung - Google Patents

Verfahren zur spracherkennung

Info

Publication number
ATE450031T1
ATE450031T1 AT06013383T AT06013383T ATE450031T1 AT E450031 T1 ATE450031 T1 AT E450031T1 AT 06013383 T AT06013383 T AT 06013383T AT 06013383 T AT06013383 T AT 06013383T AT E450031 T1 ATE450031 T1 AT E450031T1
Authority
AT
Austria
Prior art keywords
window
frame
posterior probability
frames
determined
Prior art date
Application number
AT06013383T
Other languages
English (en)
Inventor
Hagai Attias
Leo Lee
Li Deng
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 ATE450031T1 publication Critical patent/ATE450031T1/de

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/08Speech classification or search
    • G10L15/14Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B29WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29LINDEXING SCHEME ASSOCIATED WITH SUBCLASS B29C, RELATING TO PARTICULAR ARTICLES
    • B29L2030/00Pneumatic or solid tyres or parts thereof
    • B29L2030/001Beads
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/06Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063Training
    • G10L2015/0638Interactive procedures

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)
  • Image Analysis (AREA)
  • Machine Translation (AREA)
  • Complex Calculations (AREA)
  • Electric Clocks (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Alarm Systems (AREA)
  • Devices For Executing Special Programs (AREA)
AT06013383T 2004-01-20 2005-01-13 Verfahren zur spracherkennung ATE450031T1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US10/760,937 US7480615B2 (en) 2004-01-20 2004-01-20 Method of speech recognition using multimodal variational inference with switching state space models

Publications (1)

Publication Number Publication Date
ATE450031T1 true ATE450031T1 (de) 2009-12-15

Family

ID=34634563

Family Applications (2)

Application Number Title Priority Date Filing Date
AT06013383T ATE450031T1 (de) 2004-01-20 2005-01-13 Verfahren zur spracherkennung
AT05000586T ATE355589T1 (de) 2004-01-20 2005-01-13 Verfahren zur bestimmung von wahrscheinlichkeitsparametern für ein veränderliches zustandsraummodell

Family Applications After (1)

Application Number Title Priority Date Filing Date
AT05000586T ATE355589T1 (de) 2004-01-20 2005-01-13 Verfahren zur bestimmung von wahrscheinlichkeitsparametern für ein veränderliches zustandsraummodell

Country Status (7)

Country Link
US (1) US7480615B2 (de)
EP (2) EP1557823B1 (de)
JP (1) JP2005208648A (de)
KR (1) KR101120765B1 (de)
CN (1) CN100589180C (de)
AT (2) ATE450031T1 (de)
DE (2) DE602005017871D1 (de)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7912717B1 (en) 2004-11-18 2011-03-22 Albert Galick Method for uncovering hidden Markov models
EP2329399A4 (de) * 2008-09-19 2011-12-21 Newsouth Innovations Pty Ltd Verfahren zur analyse eines tonsignals
CN102087517A (zh) * 2010-07-19 2011-06-08 长春理工大学 一种减小速度插补误差的方法及硬件系统
US9785613B2 (en) * 2011-12-19 2017-10-10 Cypress Semiconductor Corporation Acoustic processing unit interface for determining senone scores using a greater clock frequency than that corresponding to received audio
CN103971685B (zh) * 2013-01-30 2015-06-10 腾讯科技(深圳)有限公司 语音命令识别方法和系统
US20160063990A1 (en) * 2014-08-26 2016-03-03 Honeywell International Inc. Methods and apparatus for interpreting clipped speech using speech recognition
PT3188060T (pt) * 2014-08-27 2023-06-27 Nec Corp Dispositivo de simulação, método de simulação e meios de memória
KR102413692B1 (ko) 2015-07-24 2022-06-27 삼성전자주식회사 음성 인식을 위한 음향 점수 계산 장치 및 방법, 음성 인식 장치 및 방법, 전자 장치
KR102192678B1 (ko) 2015-10-16 2020-12-17 삼성전자주식회사 음향 모델 입력 데이터의 정규화 장치 및 방법과, 음성 인식 장치
US9959872B2 (en) 2015-12-14 2018-05-01 International Business Machines Corporation Multimodal speech recognition for real-time video audio-based display indicia application
CN107395467B (zh) 2017-06-21 2021-08-17 北京小米移动软件有限公司 智能家居的初始化方法及装置
CN108597540A (zh) * 2018-04-11 2018-09-28 南京信息工程大学 一种基于变分模态分解和极限学习机的语音情感识别方法
CN111833867B (zh) * 2020-06-08 2023-12-05 北京嘀嘀无限科技发展有限公司 语音指令识别方法、装置、可读存储介质和电子设备
CN118708700B (zh) * 2024-08-27 2025-01-28 山东第一医科大学附属省立医院(山东省立医院) 基于状态空间模型的医疗长文本问答方法及系统

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5027406A (en) * 1988-12-06 1991-06-25 Dragon Systems, Inc. Method for interactive speech recognition and training
US5202952A (en) * 1990-06-22 1993-04-13 Dragon Systems, Inc. Large-vocabulary continuous speech prefiltering and processing system
US5864810A (en) * 1995-01-20 1999-01-26 Sri International Method and apparatus for speech recognition adapted to an individual speaker
US5778341A (en) * 1996-01-26 1998-07-07 Lucent Technologies Inc. Method of speech recognition using decoded state sequences having constrained state likelihoods
US5960395A (en) * 1996-02-09 1999-09-28 Canon Kabushiki Kaisha Pattern matching method, apparatus and computer readable memory medium for speech recognition using dynamic programming
JP4042176B2 (ja) * 1997-03-11 2008-02-06 三菱電機株式会社 音声認識方式
US6226612B1 (en) * 1998-01-30 2001-05-01 Motorola, Inc. Method of evaluating an utterance in a speech recognition system
US6678658B1 (en) * 1999-07-09 2004-01-13 The Regents Of The University Of California Speech processing using conditional observable maximum likelihood continuity mapping
US6591146B1 (en) * 1999-09-16 2003-07-08 Hewlett-Packard Development Company L.C. Method for learning switching linear dynamic system models from data
US6950796B2 (en) * 2001-11-05 2005-09-27 Motorola, Inc. Speech recognition by dynamical noise model adaptation
US6990447B2 (en) * 2001-11-15 2006-01-24 Microsoft Corportion Method and apparatus for denoising and deverberation using variational inference and strong speech models

Also Published As

Publication number Publication date
EP1701337A2 (de) 2006-09-13
US7480615B2 (en) 2009-01-20
EP1557823A2 (de) 2005-07-27
EP1557823A3 (de) 2005-08-24
DE602005000603T2 (de) 2007-06-21
DE602005017871D1 (de) 2010-01-07
KR20050076696A (ko) 2005-07-26
DE602005000603D1 (de) 2007-04-12
US20050159951A1 (en) 2005-07-21
JP2005208648A (ja) 2005-08-04
KR101120765B1 (ko) 2012-03-23
EP1701337B1 (de) 2009-11-25
CN100589180C (zh) 2010-02-10
CN1645476A (zh) 2005-07-27
ATE355589T1 (de) 2006-03-15
EP1701337A3 (de) 2007-09-05
EP1557823B1 (de) 2007-02-28

Similar Documents

Publication Publication Date Title
ATE450031T1 (de) Verfahren zur spracherkennung
CN107871496B (zh) 语音识别方法和装置
ATE330430T1 (de) Rundungskontrolle für mehrstufige interpolation
DE50009521D1 (de) Verfahren zum Ausgeben von Verkehrsinformation in einem Kraftfahrzeug
ATE438163T1 (de) Bewegungsfilterung zur videostabilisierung
SG10201900632SA (en) Picture prediction method and related apparatus
ATE511978T1 (de) Verfahren zur herstellung von blasgeformten behälter
DE60330524D1 (de) Verfahren zur Korrektur von satellitenerfassten Bildern
DE602005019848D1 (de) Verfahren zur herstellung von tad- getrocknetem ti
DE602004023555D1 (de) Spracherkennungsverfahren das Variationsinferenz mit veränderlichen Zustandsraummodellen benuzt
EP1804488A3 (de) Bewegungsschätzer und Bewegungsverfahren
DE60316912D1 (de) Verfahren zur Spracherkennung
EP2023617A3 (de) Rahmenspezifizierungsverfahren
ATE322826T1 (de) Verfahren zur herstellung von pastenextrudierten sulfonamidzusammensetzungen
NL1030729A1 (nl) Beweging-adaptief beeldverwerkingstoestel en bewegingsadaptieve werkwijze daarvoor.
ATE371923T1 (de) Verfolgen von vokaltraktresonanzen unter verwendung eines nichtlinearen prädiktors
GB0600067D0 (en) Adaptive-weighted motion estimation method and frame rate converting apparatus employing the method
ATE380811T1 (de) Verfahren zur herstellung von 1-(2s,3s)-2- benzhydril-n-(5-tert.-butyl-2- methoxybenzyl)chinuklidin-3-amin
ATE366431T1 (de) Verfahren zur regelung eines thermodynamischen prozesses
ATE465277T1 (de) Verfahren zur herstellung von leder
ATE464749T1 (de) Kodierparameterbestimmung für ein hybrides kodierschema
ATE464635T1 (de) Verfahren zum erzeugen und verwenden eines vektorcodebuchs, verfahren und einrichtung zum komprimieren von daten und verteiltes spracherkennungssystem
ATE353904T1 (de) Verfahren zur herstellung von mercaptoorganyl (alkoxysilan)
TW200731807A (en) Dynamic reference frame decision method and system
ATE387328T1 (de) Verfahren zur höhenregelung für ein fahrzeug

Legal Events

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