WO2009008055A1 - 音声認識装置、音声認識方法、および、音声認識プログラム - Google Patents

音声認識装置、音声認識方法、および、音声認識プログラム Download PDF

Info

Publication number
WO2009008055A1
WO2009008055A1 PCT/JP2007/063688 JP2007063688W WO2009008055A1 WO 2009008055 A1 WO2009008055 A1 WO 2009008055A1 JP 2007063688 W JP2007063688 W JP 2007063688W WO 2009008055 A1 WO2009008055 A1 WO 2009008055A1
Authority
WO
WIPO (PCT)
Prior art keywords
speech
word
section
similarities
time
Prior art date
Application number
PCT/JP2007/063688
Other languages
English (en)
French (fr)
Inventor
Shouji Harada
Original Assignee
Fujitsu Limited
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 Fujitsu Limited filed Critical Fujitsu Limited
Priority to PCT/JP2007/063688 priority Critical patent/WO2009008055A1/ja
Priority to CN200780053719XA priority patent/CN101689364B/zh
Priority to JP2009522448A priority patent/JP4973731B2/ja
Publication of WO2009008055A1 publication Critical patent/WO2009008055A1/ja
Priority to US12/634,208 priority patent/US8738378B2/en

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/08Speech classification or search
    • G10L15/10Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/02Feature extraction for speech recognition; Selection of recognition unit
    • G10L2015/025Phonemes, fenemes or fenones being the recognition units

Abstract

 音声認識装置(1)は、音声分析部(11)により変換された特徴量と、単語モデル生成部(16)により生成された単語モデルとの各時刻における類似度を算出する音声照合部(17)を備える。音声照合部(17)は、単語モデル生成部(16)により生成された単語モデルのうち、各時刻における類似度の中で最小の類似度あるいは各時刻における類似度から得られる全体類似度が第2閾値条件を満たし、かつ、発話音声の発声区間のうち、第1閾値条件に対応付けられた音素または音素列に対応する区間内の各時刻における類似度が第1閾値条件を満たす単語モデルを抽出し、抽出した単語モデルに対応する認識単語を認識結果として出力する。
PCT/JP2007/063688 2007-07-09 2007-07-09 音声認識装置、音声認識方法、および、音声認識プログラム WO2009008055A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
PCT/JP2007/063688 WO2009008055A1 (ja) 2007-07-09 2007-07-09 音声認識装置、音声認識方法、および、音声認識プログラム
CN200780053719XA CN101689364B (zh) 2007-07-09 2007-07-09 声音识别装置和声音识别方法
JP2009522448A JP4973731B2 (ja) 2007-07-09 2007-07-09 音声認識装置、音声認識方法、および、音声認識プログラム
US12/634,208 US8738378B2 (en) 2007-07-09 2009-12-09 Speech recognizer, speech recognition method, and speech recognition program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2007/063688 WO2009008055A1 (ja) 2007-07-09 2007-07-09 音声認識装置、音声認識方法、および、音声認識プログラム

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US12/634,208 Continuation US8738378B2 (en) 2007-07-09 2009-12-09 Speech recognizer, speech recognition method, and speech recognition program

Publications (1)

Publication Number Publication Date
WO2009008055A1 true WO2009008055A1 (ja) 2009-01-15

Family

ID=40228252

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2007/063688 WO2009008055A1 (ja) 2007-07-09 2007-07-09 音声認識装置、音声認識方法、および、音声認識プログラム

Country Status (4)

Country Link
US (1) US8738378B2 (ja)
JP (1) JP4973731B2 (ja)
CN (1) CN101689364B (ja)
WO (1) WO2009008055A1 (ja)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5533042B2 (ja) * 2010-03-04 2014-06-25 富士通株式会社 音声検索装置、音声検索方法、プログラム及び記録媒体
US9634855B2 (en) 2010-05-13 2017-04-25 Alexander Poltorak Electronic personal interactive device that determines topics of interest using a conversational agent
KR20120046627A (ko) * 2010-11-02 2012-05-10 삼성전자주식회사 화자 적응 방법 및 장치
US9384731B2 (en) * 2013-11-06 2016-07-05 Microsoft Technology Licensing, Llc Detecting speech input phrase confusion risk
CN106205601B (zh) * 2015-05-06 2019-09-03 科大讯飞股份有限公司 确定文本语音单元的方法及系统
US9922647B2 (en) * 2016-01-29 2018-03-20 International Business Machines Corporation Approach to reducing the response time of a speech interface
US20190005523A1 (en) * 2017-06-28 2019-01-03 Facebook, Inc. Identifying changes in estimated actions performed by users presented with a content item relative to different budgets for presenting the content item
US10546062B2 (en) * 2017-11-15 2020-01-28 International Business Machines Corporation Phonetic patterns for fuzzy matching in natural language processing
JP2019211599A (ja) * 2018-06-04 2019-12-12 本田技研工業株式会社 音声認識装置、音声認識方法およびプログラム
WO2020261357A1 (ja) * 2019-06-25 2020-12-30 日本電信電話株式会社 発話評価装置、発話評価方法、およびプログラム
CN111627422B (zh) * 2020-05-13 2022-07-12 广州国音智能科技有限公司 语音加速检测方法、装置、设备及可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS635395A (ja) * 1986-06-25 1988-01-11 富士通株式会社 音声認識装置
JPS63253997A (ja) * 1987-04-10 1988-10-20 富士通株式会社 音声認識装置
JPH0573087A (ja) * 1991-09-13 1993-03-26 Matsushita Electric Ind Co Ltd 音声認識方法
JP2003140683A (ja) * 2001-11-02 2003-05-16 Mitsubishi Electric Corp 音声認識装置、音声認識方法および音声認識プログラム
WO2003088209A1 (fr) * 2002-04-12 2003-10-23 Mitsubishi Denki Kabushiki Kaisha Systeme de navigation de voiture et dispositif de reconnaissance vocale de ce systeme

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62116999A (ja) 1985-11-18 1987-05-28 株式会社日立製作所 音節単位音声認識装置
JPH01302295A (ja) 1988-05-30 1989-12-06 Nippon Telegr & Teleph Corp <Ntt> 単語位置検出方法及びその音素標準パターン作成方法
JPH0772840B2 (ja) * 1992-09-29 1995-08-02 日本アイ・ビー・エム株式会社 音声モデルの構成方法、音声認識方法、音声認識装置及び音声モデルの訓練方法
JP3533696B2 (ja) * 1994-03-22 2004-05-31 三菱電機株式会社 音声認識の境界推定方法及び音声認識装置
US5737723A (en) * 1994-08-29 1998-04-07 Lucent Technologies Inc. Confusable word detection in speech recognition
WO1996010795A1 (en) * 1994-10-03 1996-04-11 Helfgott & Karas, P.C. A database accessing system
JPH08248979A (ja) 1995-03-06 1996-09-27 Fuji Xerox Co Ltd 音声認識装置
US6064959A (en) * 1997-03-28 2000-05-16 Dragon Systems, Inc. Error correction in speech recognition
JP3444108B2 (ja) * 1996-09-24 2003-09-08 三菱電機株式会社 音声認識装置
US6321195B1 (en) * 1998-04-28 2001-11-20 Lg Electronics Inc. Speech recognition method
US6400805B1 (en) * 1998-06-15 2002-06-04 At&T Corp. Statistical database correction of alphanumeric identifiers for speech recognition and touch-tone recognition
US6185530B1 (en) * 1998-08-14 2001-02-06 International Business Machines Corporation Apparatus and methods for identifying potential acoustic confusibility among words in a speech recognition system
JP2001005488A (ja) * 1999-06-18 2001-01-12 Mitsubishi Electric Corp 音声対話システム
US6434521B1 (en) * 1999-06-24 2002-08-13 Speechworks International, Inc. Automatically determining words for updating in a pronunciation dictionary in a speech recognition system
JP4201470B2 (ja) * 2000-09-12 2008-12-24 パイオニア株式会社 音声認識システム
US6859774B2 (en) * 2001-05-02 2005-02-22 International Business Machines Corporation Error corrective mechanisms for consensus decoding of speech
US7013276B2 (en) * 2001-10-05 2006-03-14 Comverse, Inc. Method of assessing degree of acoustic confusability, and system therefor
CN1198260C (zh) * 2001-11-28 2005-04-20 财团法人工业技术研究院 识别多种语言的语音识别系统的方法
US6985861B2 (en) * 2001-12-12 2006-01-10 Hewlett-Packard Development Company, L.P. Systems and methods for combining subword recognition and whole word recognition of a spoken input
US7509259B2 (en) * 2004-12-21 2009-03-24 Motorola, Inc. Method of refining statistical pattern recognition models and statistical pattern recognizers
KR100679044B1 (ko) * 2005-03-07 2007-02-06 삼성전자주식회사 사용자 적응형 음성 인식 방법 및 장치
US20070016399A1 (en) * 2005-07-12 2007-01-18 International Business Machines Corporation Method and apparatus for detecting data anomalies in statistical natural language applications
CN101326572B (zh) * 2005-12-08 2011-07-06 纽昂斯奥地利通讯有限公司 具有巨大词汇量的语音识别系统
US8626506B2 (en) * 2006-01-20 2014-01-07 General Motors Llc Method and system for dynamic nametag scoring
US8600760B2 (en) * 2006-11-28 2013-12-03 General Motors Llc Correcting substitution errors during automatic speech recognition by accepting a second best when first best is confusable

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS635395A (ja) * 1986-06-25 1988-01-11 富士通株式会社 音声認識装置
JPS63253997A (ja) * 1987-04-10 1988-10-20 富士通株式会社 音声認識装置
JPH0573087A (ja) * 1991-09-13 1993-03-26 Matsushita Electric Ind Co Ltd 音声認識方法
JP2003140683A (ja) * 2001-11-02 2003-05-16 Mitsubishi Electric Corp 音声認識装置、音声認識方法および音声認識プログラム
WO2003088209A1 (fr) * 2002-04-12 2003-10-23 Mitsubishi Denki Kabushiki Kaisha Systeme de navigation de voiture et dispositif de reconnaissance vocale de ce systeme

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
AKITA Y. ET AL.: "Hanashi Kotaba Onsei Ninshiki no Tamen no Han'yoteki na Tokeiteki Hatsuon Hendo Model", THE TRANSACTIONS OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS D-II, vol. J88-D-II, no. 9, 1 September 2005 (2005-09-01), pages 1780 - 1789, XP003018112 *

Also Published As

Publication number Publication date
CN101689364A (zh) 2010-03-31
CN101689364B (zh) 2011-11-23
JPWO2009008055A1 (ja) 2010-09-02
US20100088098A1 (en) 2010-04-08
US8738378B2 (en) 2014-05-27
JP4973731B2 (ja) 2012-07-11

Similar Documents

Publication Publication Date Title
WO2009008055A1 (ja) 音声認識装置、音声認識方法、および、音声認識プログラム
WO2009078256A1 (ja) 発音変動規則抽出装置、発音変動規則抽出方法、および発音変動規則抽出用プログラム
WO2008073850A3 (en) Method and apparatus for reading education
ATE457510T1 (de) Spracherkennungssystem mit riesigem vokabular
WO2007034478A3 (en) System and method for correcting speech
WO2007015869A3 (en) Spoken language proficiency assessment by computer
WO2007115088A3 (en) A system and method for applying dynamic contextual grammars and language models to improve automatic speech recognition accuracy
TW200638337A (en) Using a spoken utterance for disambiguation of spelling inputs into a speech recognition system
TW200601263A (en) Apparatus and method for synthesized audible response to an utterance in speaker-independent voice recognition
WO2006023631A3 (en) Document transcription system training
WO2007047587A3 (en) Method and device for recognizing human intent
WO2008111190A1 (ja) 音響モデル登録装置、話者認識装置、音響モデル登録方法及び音響モデル登録処理プログラム
Hatmi et al. Incorporating named entity recognition into the speech transcription process
Schuller et al. Late fusion of individual engines for improved recognition of negative emotion in speech-learning vs. democratic vote
Garud et al. Development of hmm based automatic speech recognition system for Indian english
JP2012255867A (ja) 音声認識装置
Matsuda et al. Speech recognition system robust to noise and speaking styles.
WO2014197592A3 (en) Enhanced human machine interface through hybrid word recognition and dynamic speech synthesis tuning
WO2006034152A3 (en) Discriminative training of document transcription system
Macias-Guarasa et al. Initial Evaluation of a Preselection Module for a Flexible Large Vocabulary Speech Recognition System in Telephone Environment
Anu et al. Sentence segmentation for speech processing
Lindgren Speech recognition using features extracted from phase space reconstructions
Shaik et al. The RWTH Aachen German and English LVCSR systems for IWSLT-2013
Stouten et al. Recognition of foreign names spoken by native speakers
Koller et al. Exploiting variety-dependent phones in Portuguese variety identification

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 200780053719.X

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07790509

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2009522448

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07790509

Country of ref document: EP

Kind code of ref document: A1