DE19581663T1 - Verfahren zum Training neuraler Netze, die für eine Spracherkennung verwendet werden - Google Patents

Verfahren zum Training neuraler Netze, die für eine Spracherkennung verwendet werden

Info

Publication number
DE19581663T1
DE19581663T1 DE19581663T DE19581663T DE19581663T1 DE 19581663 T1 DE19581663 T1 DE 19581663T1 DE 19581663 T DE19581663 T DE 19581663T DE 19581663 T DE19581663 T DE 19581663T DE 19581663 T1 DE19581663 T1 DE 19581663T1
Authority
DE
Germany
Prior art keywords
procedure
speech recognition
neural networks
training neural
training
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.)
Ceased
Application number
DE19581663T
Other languages
English (en)
Inventor
Shay-Ping Thomas Wang
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.)
Motorola Solutions Inc
Original Assignee
Motorola Inc
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 Motorola Inc filed Critical Motorola Inc
Publication of DE19581663T1 publication Critical patent/DE19581663T1/de
Ceased 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
    • G10L15/16—Speech classification or search using artificial neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/245—Classification techniques relating to the decision surface
    • G06F18/2453—Classification techniques relating to the decision surface non-linear, e.g. polynomial classifier
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G10L15/26—Speech to text systems
    • 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
    • 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
    • G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • 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
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Nonlinear Science (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
DE19581663T 1994-06-03 1995-04-25 Verfahren zum Training neuraler Netze, die für eine Spracherkennung verwendet werden Ceased DE19581663T1 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/253,893 US5509103A (en) 1994-06-03 1994-06-03 Method of training neural networks used for speech recognition
PCT/US1995/005002 WO1995034035A1 (en) 1994-06-03 1995-04-25 Method of training neural networks used for speech recognition

Publications (1)

Publication Number Publication Date
DE19581663T1 true DE19581663T1 (de) 1997-05-07

Family

ID=22962136

Family Applications (1)

Application Number Title Priority Date Filing Date
DE19581663T Ceased DE19581663T1 (de) 1994-06-03 1995-04-25 Verfahren zum Training neuraler Netze, die für eine Spracherkennung verwendet werden

Country Status (7)

Country Link
US (1) US5509103A (de)
CN (1) CN1151218A (de)
AU (1) AU2427095A (de)
CA (1) CA2190631C (de)
DE (1) DE19581663T1 (de)
GB (1) GB2303237B (de)
WO (1) WO1995034035A1 (de)

Families Citing this family (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5697369A (en) * 1988-12-22 1997-12-16 Biofield Corp. Method and apparatus for disease, injury and bodily condition screening or sensing
US5749072A (en) * 1994-06-03 1998-05-05 Motorola Inc. Communications device responsive to spoken commands and methods of using same
US5621848A (en) * 1994-06-06 1997-04-15 Motorola, Inc. Method of partitioning a sequence of data frames
US5724486A (en) * 1995-08-21 1998-03-03 Motorola Inc. Method for structuring an expert system utilizing one or more polynomial processors
US5745874A (en) * 1996-03-04 1998-04-28 National Semiconductor Corporation Preprocessor for automatic speech recognition system
US5917891A (en) * 1996-10-07 1999-06-29 Northern Telecom, Limited Voice-dialing system using adaptive model of calling behavior
US6167117A (en) * 1996-10-07 2000-12-26 Nortel Networks Limited Voice-dialing system using model of calling behavior
US5905789A (en) * 1996-10-07 1999-05-18 Northern Telecom Limited Call-forwarding system using adaptive model of user behavior
US5912949A (en) * 1996-11-05 1999-06-15 Northern Telecom Limited Voice-dialing system using both spoken names and initials in recognition
US5864807A (en) * 1997-02-25 1999-01-26 Motorola, Inc. Method and apparatus for training a speaker recognition system
US5995924A (en) * 1997-05-05 1999-11-30 U.S. West, Inc. Computer-based method and apparatus for classifying statement types based on intonation analysis
US6192353B1 (en) * 1998-02-09 2001-02-20 Motorola, Inc. Multiresolutional classifier with training system and method
US6131089A (en) * 1998-05-04 2000-10-10 Motorola, Inc. Pattern classifier with training system and methods of operation therefor
US7369993B1 (en) 2000-11-02 2008-05-06 At&T Corp. System and method of pattern recognition in very high-dimensional space
US7006969B2 (en) * 2000-11-02 2006-02-28 At&T Corp. System and method of pattern recognition in very high-dimensional space
WO2002091358A1 (en) * 2001-05-08 2002-11-14 Intel Corporation Method and apparatus for rejection of speech recognition results in accordance with confidence level
WO2002091355A1 (en) * 2001-05-08 2002-11-14 Intel Corporation High-order entropy error functions for neural classifiers
KR100486735B1 (ko) * 2003-02-28 2005-05-03 삼성전자주식회사 최적구획 분류신경망 구성방법과 최적구획 분류신경망을이용한 자동 레이블링방법 및 장치
FR2881857B1 (fr) * 2005-02-04 2008-05-23 Bernard Angeniol Outil informatique de prevision
CN100446029C (zh) * 2007-02-15 2008-12-24 杨志军 智能机器视觉识别系统中的信号处理电路
EP2221805B1 (de) * 2009-02-20 2014-06-25 Nuance Communications, Inc. Verfahren zum automatisierten Training einer Vielzahl künstlicher neuronaler Netzwerke
US9240184B1 (en) * 2012-11-15 2016-01-19 Google Inc. Frame-level combination of deep neural network and gaussian mixture models
US9508347B2 (en) * 2013-07-10 2016-11-29 Tencent Technology (Shenzhen) Company Limited Method and device for parallel processing in model training
CN104021373B (zh) * 2014-05-27 2017-02-15 江苏大学 一种半监督语音特征可变因素分解方法
US9786270B2 (en) 2015-07-09 2017-10-10 Google Inc. Generating acoustic models
US10229672B1 (en) 2015-12-31 2019-03-12 Google Llc Training acoustic models using connectionist temporal classification
US10878318B2 (en) 2016-03-28 2020-12-29 Google Llc Adaptive artificial neural network selection techniques
CN109313540B (zh) * 2016-05-13 2021-12-03 微软技术许可有限责任公司 口语对话系统的两阶段训练
US20180018973A1 (en) 2016-07-15 2018-01-18 Google Inc. Speaker verification
US10706840B2 (en) 2017-08-18 2020-07-07 Google Llc Encoder-decoder models for sequence to sequence mapping
CN108053025B (zh) * 2017-12-08 2020-01-24 合肥工业大学 多柱神经网络医学影像分析方法及装置
US11380315B2 (en) * 2019-03-09 2022-07-05 Cisco Technology, Inc. Characterizing accuracy of ensemble models for automatic speech recognition by determining a predetermined number of multiple ASR engines based on their historical performance
CN110767231A (zh) * 2019-09-19 2020-02-07 平安科技（深圳）有限公司 一种基于时延神经网络的声控设备唤醒词识别方法及装置
CN111723873A (zh) * 2020-06-29 2020-09-29 南方电网科学研究院有限责任公司 一种电力序列数据分类方法和装置
CN114038465B (zh) * 2021-04-28 2022-08-23 北京有竹居网络技术有限公司 语音处理方法、装置和电子设备

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2689292A1 (fr) * 1992-03-27 1993-10-01 Lorraine Laminage Procédé et système de reconnaissance vocale à réseau neuronal.
EP0574951A2 (de) * 1992-06-18 1993-12-22 Seiko Epson Corporation Spracherkennungssystem

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE69030561T2 (de) * 1989-12-28 1997-10-09 Sharp Kk Spracherkennungseinrichtung
US5365592A (en) * 1990-07-19 1994-11-15 Hughes Aircraft Company Digital voice detection apparatus and method using transform domain processing
US5212765A (en) * 1990-08-03 1993-05-18 E. I. Du Pont De Nemours & Co., Inc. On-line training neural network system for process control
US5408588A (en) * 1991-06-06 1995-04-18 Ulug; Mehmet E. Artificial neural network method and architecture

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2689292A1 (fr) * 1992-03-27 1993-10-01 Lorraine Laminage Procédé et système de reconnaissance vocale à réseau neuronal.
EP0574951A2 (de) * 1992-06-18 1993-12-22 Seiko Epson Corporation Spracherkennungssystem

Also Published As

Publication number Publication date
CA2190631A1 (en) 1995-12-14
GB2303237B (en) 1997-12-17
CA2190631C (en) 2000-02-22
GB9625250D0 (en) 1997-01-22
WO1995034035A1 (en) 1995-12-14
AU2427095A (en) 1996-01-04
GB2303237A (en) 1997-02-12
CN1151218A (zh) 1997-06-04
US5509103A (en) 1996-04-16

Similar Documents

Publication Publication Date Title
DE19581663T1 (de) Verfahren zum Training neuraler Netze, die für eine Spracherkennung verwendet werden
DE69708837T2 (de) Hochfeste, hochzähe aluminiumlegierung und verfahren zu deren herstellung
DE69523965D1 (de) Erkennungsverfahren für eine zweidimensionale Kodierung
DE69527801T2 (de) Ultrahochfeste stähle und verfahren zu deren herstellung
DE69421405D1 (de) Verbesserter zahnseidenstoff aus expandiertem ptfe, und verfahren zu dessen herstellung
DE59708917D1 (de) Verpackung für Zigaretten, sowie Verfahren und Vorrichtung zum Herstellen derselben
DE69301129D1 (de) Gesichtsschminkverfahren, insbesonders für die Augen und Vorrichtung zur Auführung des Verfahrens
DE69627709D1 (de) N-(unsubstituierte oder substituierte)-4-substituierte-6-(unsubstituierte oder substituierte)phenoxy-2-pyridincarboxamide oder -thiocarboxamide, verfahren zu deren herstellung sowie herbizide
DE69518451D1 (de) Verfahren zum Herstellen alterungsbeständiger, gut verformbarer Stahlbleche für die Fertigung von Dosen
DE69411798T2 (de) Isolierten Aderpaaren, sowie Verfahren und Apparat zur Herstellung derselben
DE69825253D1 (de) Verfahren für die herstellung von 1,1,1,3,3-pentafluorpropen und 2-chlor-pentafluorpropen
DE69501978T2 (de) Rollvorrichtung für längliche Gegenstände, insbesondere für die Herstellung von Tabakprodukten
ATE193733T1 (de) Stahl für die herstellung von teilbaren maschinenteilen und maschinenteile, hergestellt aus diesen stahl
DE69114909D1 (de) Verfahren zum Kugeligglühen.
DE69616724D1 (de) Verfahren und System für die Spracherkennung
DE69532018D1 (de) Druckkopf, Druckvorrichtung und -verfahren, die den Druckkopf benutzen
DE59502580D1 (de) Lösliche Copolymerisate für die Haarkosmetik
DE69610544D1 (de) Hochfeste, hochduktile titanlegierung und verfahren zu deren herstellung
DE69724350D1 (de) Verfahren zum Erhöhen der Anti-Benetzbarkeit eines Körpers, Körper dementsprechend behandelt.
DE69300039D1 (de) Mehrrollensatz für Druckverschliessvorrichtung und Verfahren zum Verschliessen.
DE69511323T2 (de) Emulsionspolymerisationsinhibitor und Suspensionspolymerisationsverfahren, die diesen Verwenden
DE3883309D1 (de) Kohlenstoffhaltiger rohrfoermiger zylinder und verfahren zu seiner herstellung.
DE3865927D1 (de) Tetrahydroindazolyl-benzoxazine, verfahren zu deren herstellung und deren anwendung.
DE68904897D1 (de) Verbindungs- und anschlussblock zwischen nachgiebigen, elastomerischen leitungen, verfahren und vorrichtung zu seiner herstellung.
DE59709011D1 (de) Bahnförmiges halbzeug, insbesondere putztapete, und verfahren zu dessen herstellung

Legal Events

Date Code Title Description
OP8 Request for examination as to paragraph 44 patent law
8131 Rejection