JP2006011257A5 - - Google Patents

Download PDF

Info

Publication number
JP2006011257A5
JP2006011257A5 JP2004191460A JP2004191460A JP2006011257A5 JP 2006011257 A5 JP2006011257 A5 JP 2006011257A5 JP 2004191460 A JP2004191460 A JP 2004191460A JP 2004191460 A JP2004191460 A JP 2004191460A JP 2006011257 A5 JP2006011257 A5 JP 2006011257A5
Authority
JP
Japan
Prior art keywords
acoustic model
likelihood
speech
state
calculating
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.)
Granted
Application number
JP2004191460A
Other languages
English (en)
Japanese (ja)
Other versions
JP2006011257A (ja
JP4541781B2 (ja
Filing date
Publication date
Application filed filed Critical
Priority to JP2004191460A priority Critical patent/JP4541781B2/ja
Priority claimed from JP2004191460A external-priority patent/JP4541781B2/ja
Priority to US11/165,167 priority patent/US7565290B2/en
Publication of JP2006011257A publication Critical patent/JP2006011257A/ja
Publication of JP2006011257A5 publication Critical patent/JP2006011257A5/ja
Application granted granted Critical
Publication of JP4541781B2 publication Critical patent/JP4541781B2/ja
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

JP2004191460A 2004-06-29 2004-06-29 音声認識装置および方法 Expired - Fee Related JP4541781B2 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2004191460A JP4541781B2 (ja) 2004-06-29 2004-06-29 音声認識装置および方法
US11/165,167 US7565290B2 (en) 2004-06-29 2005-06-24 Speech recognition method and apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2004191460A JP4541781B2 (ja) 2004-06-29 2004-06-29 音声認識装置および方法

Publications (3)

Publication Number Publication Date
JP2006011257A JP2006011257A (ja) 2006-01-12
JP2006011257A5 true JP2006011257A5 (https=) 2010-02-25
JP4541781B2 JP4541781B2 (ja) 2010-09-08

Family

ID=35507163

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2004191460A Expired - Fee Related JP4541781B2 (ja) 2004-06-29 2004-06-29 音声認識装置および方法

Country Status (2)

Country Link
US (1) US7565290B2 (https=)
JP (1) JP4541781B2 (https=)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007142840A (ja) * 2005-11-18 2007-06-07 Canon Inc 情報処理装置及び情報処理方法
JP4188989B2 (ja) * 2006-09-15 2008-12-03 本田技研工業株式会社 音声認識装置、音声認識方法、及び音声認識プログラム
JP4758919B2 (ja) * 2007-01-22 2011-08-31 日本放送協会 音声認識装置及び音声認識プログラム
JP2008225254A (ja) * 2007-03-14 2008-09-25 Canon Inc 音声合成装置及び方法並びにプログラム
US8275615B2 (en) 2007-07-13 2012-09-25 International Business Machines Corporation Model weighting, selection and hypotheses combination for automatic speech recognition and machine translation
JP5273844B2 (ja) * 2008-03-31 2013-08-28 Ｋｄｄｉ株式会社 字幕ずれ推定装置、字幕ずれ補正装置、再生装置および放送装置
CN102027534B (zh) * 2008-05-16 2013-07-31 日本电气株式会社 语言模型得分前瞻值赋值方法及设备
JP5246948B2 (ja) * 2009-03-27 2013-07-24 Ｋｄｄｉ株式会社 字幕ずれ補正装置、再生装置および放送装置
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
CN105869624B (zh) * 2016-03-29 2019-05-10 腾讯科技（深圳）有限公司 数字语音识别中语音解码网络的构建方法及装置
JP6585112B2 (ja) * 2017-03-17 2019-10-02 株式会社東芝 音声キーワード検出装置および音声キーワード検出方法
CN112242144A (zh) * 2019-07-17 2021-01-19 百度在线网络技术（北京）有限公司 基于流式注意力模型的语音识别解码方法、装置、设备以及计算机可读存储介质

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2712856B2 (ja) * 1991-03-08 1998-02-16 三菱電機株式会社 音声認識装置
JP3397372B2 (ja) * 1993-06-16 2003-04-14 キヤノン株式会社 音声認識方法及び装置
US5621859A (en) * 1994-01-19 1997-04-15 Bbn Corporation Single tree method for grammar directed, very large vocabulary speech recognizer
JP3450411B2 (ja) * 1994-03-22 2003-09-22 キヤノン株式会社 音声情報処理方法及び装置
JP3581401B2 (ja) * 1994-10-07 2004-10-27 キヤノン株式会社 音声認識方法
JP3453456B2 (ja) * 1995-06-19 2003-10-06 キヤノン株式会社 状態共有モデルの設計方法及び装置ならびにその状態共有モデルを用いた音声認識方法および装置
JP3459712B2 (ja) * 1995-11-01 2003-10-27 キヤノン株式会社 音声認識方法及び装置及びコンピュータ制御装置
JPH1097276A (ja) * 1996-09-20 1998-04-14 Canon Inc 音声認識方法及び装置並びに記憶媒体
US6076056A (en) * 1997-09-19 2000-06-13 Microsoft Corporation Speech recognition system for recognizing continuous and isolated speech
US6018628A (en) * 1998-06-16 2000-01-25 Sun Microsystems, Inc. Method of implementing parameterized types to be compatible with existing unparameterized libraries
US6542866B1 (en) * 1999-09-22 2003-04-01 Microsoft Corporation Speech recognition method and apparatus utilizing multiple feature streams
JP4543294B2 (ja) * 2000-03-14 2010-09-15 ソニー株式会社 音声認識装置および音声認識方法、並びに記録媒体
JP2001312293A (ja) * 2000-04-28 2001-11-09 Matsushita Electric Ind Co Ltd 音声認識方法およびその装置、並びにコンピュータ読み取り可能な記憶媒体
JP3728177B2 (ja) * 2000-05-24 2005-12-21 キヤノン株式会社 音声処理システム、装置、方法及び記憶媒体
AU2000276400A1 (en) * 2000-09-30 2002-04-15 Intel Corporation Search method based on single triphone tree for large vocabulary continuous speech recognizer
JP2002149187A (ja) * 2000-11-07 2002-05-24 Sony Corp 音声認識装置および音声認識方法、並びに記録媒体
JP2002189494A (ja) * 2000-12-19 2002-07-05 Atr Onsei Gengo Tsushin Kenkyusho:Kk 音声認識システム
JP2002215187A (ja) 2001-01-23 2002-07-31 Matsushita Electric Ind Co Ltd 音声認識方法及びその装置
JP3885002B2 (ja) * 2002-06-28 2007-02-21 キヤノン株式会社 情報処理装置およびその方法

Similar Documents

Publication Publication Date Title
Koller et al. Continuous sign language recognition: Towards large vocabulary statistical recognition systems handling multiple signers
JP2006011257A5 (https=)
US9721561B2 (en) Method and apparatus for speech recognition using neural networks with speaker adaptation
WO2016188558A1 (en) Select one of plurality of neural networks
KR100406604B1 (ko) 음성인식방법및장치
US20160322042A1 (en) Fast deep neural network feature transformation via optimized memory bandwidth utilization
JP2017525993A5 (https=)
US10515312B1 (en) Neural network model compaction using selective unit removal
WO2016139670A8 (en) System and method for generating accurate speech transcription from natural speech audio signals
US9886948B1 (en) Neural network processing of multiple feature streams using max pooling and restricted connectivity
CN112578419B (zh) 一种基于gru网络和卡尔曼滤波的gps数据重构方法
JP2022515048A5 (https=)
WO2007118030A3 (en) Methods and systems for optimizing model adaptation for a speech recognition system
US9177552B2 (en) Method and apparatus for setting selected recognition parameters to minimize an application cost function
CN105989839B (zh) 语音识别方法和装置
JP4541781B2 (ja) 音声認識装置および方法
Chen et al. A novel keyword+ LVCSR-filler based grammar network representation for spoken keyword search
BenZeghiba et al. Phonotactic Language Recognition Using MLP Features.
Saon et al. A comparison of two optimization techniques for sequence discriminative training of deep neural networks
Nolden et al. Extended search space pruning in LVCSR
WO2017159207A1 (ja) 処理実行装置、処理実行装置の制御方法、および制御プログラム
Tian et al. Deep neural networks based speaker modeling at different levels of phonetic granularity
KR100612843B1 (ko) 은닉 마코프 모델를 위한 확률밀도함수 보상 방법, 그에따른 음성 인식 방법 및 장치
CN105931636A (zh) 多语系语音辨识装置及其方法
RU2698773C2 (ru) Устройство и способ распознавания речи