ATE447754T1 - Kompression gausscher modelle - Google Patents

Kompression gausscher modelle

Info

Publication number
ATE447754T1
ATE447754T1 AT06025047T AT06025047T ATE447754T1 AT E447754 T1 ATE447754 T1 AT E447754T1 AT 06025047 T AT06025047 T AT 06025047T AT 06025047 T AT06025047 T AT 06025047T AT E447754 T1 ATE447754 T1 AT E447754T1
Authority
AT
Austria
Prior art keywords
compression
gaussian distributions
gaussian models
gaussian
centroid
Prior art date
Application number
AT06025047T
Other languages
English (en)
Inventor
Alejandro Acero
Michael D Plumpe
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 ATE447754T1 publication Critical patent/ATE447754T1/de

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
    • G01R29/08—Measuring electromagnetic field characteristics
    • G01R29/0807—Measuring electromagnetic field characteristics characterised by the application
    • G01R29/0814—Field measurements related to measuring influence on or from apparatus, components or humans, e.g. in ESD, EMI, EMC, EMP testing, measuring radiation leakage; detecting presence of micro- or radiowave emitters; dosimetry; testing shielding; measurements related to lightning
    • 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
    • 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
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/285—Memory allocation or algorithm optimisation to reduce hardware requirements

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Probability & Statistics with Applications (AREA)
  • Electromagnetism (AREA)
  • General Physics & Mathematics (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Steroid Compounds (AREA)
AT06025047T 2003-03-13 2004-03-12 Kompression gausscher modelle ATE447754T1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US10/388,260 US7571097B2 (en) 2003-03-13 2003-03-13 Method for training of subspace coded gaussian models

Publications (1)

Publication Number Publication Date
ATE447754T1 true ATE447754T1 (de) 2009-11-15

Family

ID=32771632

Family Applications (2)

Application Number Title Priority Date Filing Date
AT06025047T ATE447754T1 (de) 2003-03-13 2004-03-12 Kompression gausscher modelle
AT04006013T ATE347727T1 (de) 2003-03-13 2004-03-12 Kompression gausscher modelle

Family Applications After (1)

Application Number Title Priority Date Filing Date
AT04006013T ATE347727T1 (de) 2003-03-13 2004-03-12 Kompression gausscher modelle

Country Status (7)

Country Link
US (1) US7571097B2 (de)
EP (2) EP1758097B1 (de)
JP (1) JP4672272B2 (de)
KR (1) KR20040081393A (de)
CN (1) CN100580771C (de)
AT (2) ATE447754T1 (de)
DE (2) DE602004003512T2 (de)

Families Citing this family (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7499857B2 (en) * 2003-05-15 2009-03-03 Microsoft Corporation Adaptation of compressed acoustic models
KR100612843B1 (ko) * 2004-02-28 2006-08-14 삼성전자주식회사 은닉 마코프 모델를 위한 확률밀도함수 보상 방법, 그에따른 음성 인식 방법 및 장치
US20060136210A1 (en) * 2004-12-16 2006-06-22 Sony Corporation System and method for tying variance vectors for speech recognition
US7634405B2 (en) * 2005-01-24 2009-12-15 Microsoft Corporation Palette-based classifying and synthesizing of auditory information
US7729909B2 (en) * 2005-03-04 2010-06-01 Panasonic Corporation Block-diagonal covariance joint subspace tying and model compensation for noise robust automatic speech recognition
WO2007003505A1 (fr) * 2005-07-01 2007-01-11 France Telecom Procédé et dispositif de segmentation et de labellisation du contenu d'un signal d'entrée se présentant sous la forme d'un flux continu de données d'entrée indifférenciées.
KR100664960B1 (ko) * 2005-10-06 2007-01-04 삼성전자주식회사 음성 인식 장치 및 방법
US20070088552A1 (en) * 2005-10-17 2007-04-19 Nokia Corporation Method and a device for speech recognition
CN101188107B (zh) * 2007-09-28 2011-09-07 中国民航大学 一种基于小波包分解及混合高斯模型估计的语音识别方法
US8239195B2 (en) * 2008-09-23 2012-08-07 Microsoft Corporation Adapting a compressed model for use in speech recognition
EP2431969B1 (de) * 2010-09-15 2013-04-03 Svox AG Spracherkennung mit kleinem Rechenaufwand und reduziertem Quantisierungsfehler
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
CN104657388A (zh) * 2013-11-22 2015-05-27 阿里巴巴集团控股有限公司 一种数据处理方法和装置
WO2015116150A1 (en) * 2014-01-31 2015-08-06 Hewlett-Packard Development Company, L.P. Segments of contacts
US9858922B2 (en) 2014-06-23 2018-01-02 Google Inc. Caching speech recognition scores
US9299347B1 (en) 2014-10-22 2016-03-29 Google Inc. Speech recognition using associative mapping
US20180137539A1 (en) * 2015-05-01 2018-05-17 Open Text Corporation Context association
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
US20180018973A1 (en) 2016-07-15 2018-01-18 Google Inc. Speaker verification
US10565713B2 (en) 2016-11-15 2020-02-18 Samsung Electronics Co., Ltd. Image processing apparatus and method
US10706840B2 (en) 2017-08-18 2020-07-07 Google Llc Encoder-decoder models for sequence to sequence mapping
BR112020023552A2 (pt) * 2018-05-18 2021-02-09 Greeneden U.S. Holdings Ii, Llc métodos para treinar um modelo de confiança em um sistema de reconhecimento automático de fala e para converter entrada de fala em texto usando modelagem de confiança com uma abordagem multiclasse, e, sistema destinado a converter fala de entrada em texto.
US20220051139A1 (en) * 2018-12-28 2022-02-17 Telefonaktiebolaget Lm Ericsson (Publ) Wireless device, a network node and methods therein for training of a machine learning model
US11176924B2 (en) * 2020-01-09 2021-11-16 International Business Machines Corporation Reduced miss rate in sound to text conversion using banach spaces
US20210375270A1 (en) * 2020-06-02 2021-12-02 Knowles Electronics, Llc Methods and systems for confusion reduction for compressed acoustic models
CN114139621A (zh) * 2021-11-29 2022-03-04 国家电网有限公司大数据中心 确定模型分类性能标识的方法、装置、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
US5182773A (en) * 1991-03-22 1993-01-26 International Business Machines Corporation Speaker-independent label coding apparatus
US5271088A (en) * 1991-05-13 1993-12-14 Itt Corporation Automated sorting of voice messages through speaker spotting
US5278942A (en) * 1991-12-05 1994-01-11 International Business Machines Corporation Speech coding apparatus having speaker dependent prototypes generated from nonuser reference data
US5765127A (en) * 1992-03-18 1998-06-09 Sony Corp High efficiency encoding method
JP2531073B2 (ja) * 1993-01-14 1996-09-04 日本電気株式会社 音声認識システム
US5793891A (en) * 1994-07-07 1998-08-11 Nippon Telegraph And Telephone Corporation Adaptive training method for pattern recognition
DE69613338T2 (de) * 1995-08-28 2002-05-29 Koninkl Philips Electronics Nv Verfahren und system zur mustererkennung mittels baumstrukturierten wahrscheinlichkeitsdichten
JP2871561B2 (ja) * 1995-11-30 1999-03-17 株式会社エイ・ティ・アール音声翻訳通信研究所 不特定話者モデル生成装置及び音声認識装置
US6317712B1 (en) * 1998-02-03 2001-11-13 Texas Instruments Incorporated Method of phonetic modeling using acoustic decision tree
US6141641A (en) 1998-04-15 2000-10-31 Microsoft Corporation Dynamically configurable acoustic model for speech recognition system
US6687336B1 (en) * 1999-09-30 2004-02-03 Teradyne, Inc. Line qualification with neural networks
US6526379B1 (en) * 1999-11-29 2003-02-25 Matsushita Electric Industrial Co., Ltd. Discriminative clustering methods for automatic speech recognition
CN1452753A (zh) * 2000-02-28 2003-10-29 西门子公司 系统模型化的方法和装置
US6931351B2 (en) * 2001-04-20 2005-08-16 International Business Machines Corporation Decision making in classification problems

Also Published As

Publication number Publication date
JP4672272B2 (ja) 2011-04-20
EP1758097A3 (de) 2007-06-20
CN100580771C (zh) 2010-01-13
EP1457967A3 (de) 2004-12-01
DE602004003512T2 (de) 2007-09-20
DE602004003512D1 (de) 2007-01-18
KR20040081393A (ko) 2004-09-21
EP1457967B1 (de) 2006-12-06
US20040181408A1 (en) 2004-09-16
EP1758097A2 (de) 2007-02-28
CN1538382A (zh) 2004-10-20
EP1758097B1 (de) 2009-11-04
US7571097B2 (en) 2009-08-04
JP2004280098A (ja) 2004-10-07
DE602004023975D1 (de) 2009-12-17
ATE347727T1 (de) 2006-12-15
EP1457967A2 (de) 2004-09-15

Similar Documents

Publication Publication Date Title
ATE447754T1 (de) Kompression gausscher modelle
WO2002095533A3 (en) Model selection for cluster data analysis
WO2008045521A3 (en) Face-based image clustering
JP2004280098A5 (de)
CN102254180B (zh) 一种基于几何特征的人脸美感分析方法
WO2004091733A3 (en) Training apparatus and methods
WO2006110242A3 (en) Model optimization method and system using zeta statistic
EP1172740A3 (de) SQL-basierter analytischen Algorithmus für die Analyse von Gruppen
CN103971095B (zh) 基于多尺度lbp和稀疏编码的大规模人脸表情识别方法
WO2006041816A3 (en) Methodologies linking patterns from multi-modality datasets
CA2486182A1 (en) Modeling geological objects in faulted formations
CN103593674A (zh) 一种颈部淋巴结超声图像特征选择方法
Al-Daoud A new algorithm for cluster initialization
WO2005006278A3 (en) Systems and methods for training component-based object identification systems
CN108717527A (zh) 基于姿态先验的人脸对齐方法
CN105844106A (zh) 一种健康提醒方法及装置
Albatineh et al. MCS: A method for finding the number of clusters
WO2009060722A1 (ja) 類似画像検索装置
CN110309696A (zh) 基于深度学习及多聚类中心损失函数的摊贩物品分类方法
CN110047509B (zh) 一种两级子空间划分方法及装置
EP3971782A3 (de) Neuronale netzwerkauswahl
Mancas et al. On modeling first order predicate calculus using the elementary mathematical data model in MatBase DBMS.
CN113722374B (zh) 基于后缀树的时间序列变长模体挖掘方法
CN2739282Y (zh) 拼装方便的木地板块
Yang et al. Learning to recognize the art style of paintings using multi-cues

Legal Events

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