CN103971677B - 一种声学语言模型训练方法和装置 - Google Patents
一种声学语言模型训练方法和装置 Download PDFInfo
- Publication number
- CN103971677B CN103971677B CN201310040085.1A CN201310040085A CN103971677B CN 103971677 B CN103971677 B CN 103971677B CN 201310040085 A CN201310040085 A CN 201310040085A CN 103971677 B CN103971677 B CN 103971677B
- Authority
- CN
- China
- Prior art keywords
- class label
- language model
- participle
- vocabulary
- acoustics
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012549 training Methods 0.000 title claims abstract description 33
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 101000934888 Homo sapiens Succinate dehydrogenase cytochrome b560 subunit, mitochondrial Proteins 0.000 description 1
- 102100025393 Succinate dehydrogenase cytochrome b560 subunit, mitochondrial Human genes 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G10L15/06—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
- G10L15/04—Segmentation; Word boundary detection
- G10L15/05—Word boundary detection
-
- 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
- G10L2015/0631—Creating reference templates; Clustering
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
Description
Claims (14)
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310040085.1A CN103971677B (zh) | 2013-02-01 | 2013-02-01 | 一种声学语言模型训练方法和装置 |
JP2015555551A JP5901001B1 (ja) | 2013-02-01 | 2013-10-25 | 音響言語モデルトレーニングのための方法およびデバイス |
BR112015018205-4A BR112015018205B1 (pt) | 2013-02-01 | 2013-10-25 | Método e sistema para a formação de modelo de linguagem acústica, e meio de armazenamento legível por computador. |
CA2899532A CA2899532C (en) | 2013-02-01 | 2013-10-25 | Method and device for acoustic language model training |
PCT/CN2013/085948 WO2014117548A1 (en) | 2013-02-01 | 2013-10-25 | Method and device for acoustic language model training |
US14/109,845 US9396723B2 (en) | 2013-02-01 | 2013-12-17 | Method and device for acoustic language model training |
TW103100469A TWI512719B (zh) | 2013-02-01 | 2014-01-07 | An acoustic language model training method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310040085.1A CN103971677B (zh) | 2013-02-01 | 2013-02-01 | 一种声学语言模型训练方法和装置 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103971677A CN103971677A (zh) | 2014-08-06 |
CN103971677B true CN103971677B (zh) | 2015-08-12 |
Family
ID=51241096
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310040085.1A Active CN103971677B (zh) | 2013-02-01 | 2013-02-01 | 一种声学语言模型训练方法和装置 |
Country Status (6)
Country | Link |
---|---|
JP (1) | JP5901001B1 (zh) |
CN (1) | CN103971677B (zh) |
BR (1) | BR112015018205B1 (zh) |
CA (1) | CA2899532C (zh) |
TW (1) | TWI512719B (zh) |
WO (1) | WO2014117548A1 (zh) |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106486114A (zh) * | 2015-08-28 | 2017-03-08 | 株式会社东芝 | 改进语言模型的方法和装置以及语音识别方法和装置 |
JP6312942B2 (ja) * | 2015-10-09 | 2018-04-18 | 三菱電機株式会社 | 言語モデル生成装置、言語モデル生成方法とそのプログラム |
CN105654945B (zh) * | 2015-10-29 | 2020-03-06 | 乐融致新电子科技(天津)有限公司 | 一种语言模型的训练方法及装置、设备 |
CN107204184B (zh) * | 2017-05-10 | 2018-08-03 | 平安科技(深圳)有限公司 | 语音识别方法及系统 |
CN109427330B (zh) * | 2017-09-05 | 2023-04-07 | 中国科学院声学研究所 | 一种基于统计语言模型得分规整的语音识别方法及系统 |
TWI639997B (zh) * | 2017-09-28 | 2018-11-01 | 大仁科技大學 | 基於機率規則之對話理解方法 |
CN110019305B (zh) * | 2017-12-18 | 2024-03-15 | 上海智臻智能网络科技股份有限公司 | 知识库扩展方法及存储介质、终端 |
CN110083820B (zh) * | 2018-01-26 | 2023-06-27 | 普天信息技术有限公司 | 一种基准分词模型的改进方法及装置 |
CN108197116B (zh) * | 2018-01-31 | 2021-05-28 | 天闻数媒科技(北京)有限公司 | 一种中文文本分词的方法、装置、分词设备及存储介质 |
CN110648657B (zh) * | 2018-06-27 | 2024-02-02 | 北京搜狗科技发展有限公司 | 一种语言模型训练方法、构建方法和装置 |
CN109616121A (zh) * | 2018-11-28 | 2019-04-12 | 北京捷通华声科技股份有限公司 | 一种数字转换方法和装置 |
CN109949797B (zh) * | 2019-03-11 | 2021-11-12 | 北京百度网讯科技有限公司 | 一种训练语料的生成方法、装置、设备及存储介质 |
CN110110041B (zh) * | 2019-03-15 | 2022-02-15 | 平安科技(深圳)有限公司 | 错词纠正方法、装置、计算机装置及存储介质 |
CN111694962A (zh) * | 2019-03-15 | 2020-09-22 | 阿里巴巴集团控股有限公司 | 数据处理方法和装置 |
US11417313B2 (en) | 2019-04-23 | 2022-08-16 | Lg Electronics Inc. | Speech synthesizer using artificial intelligence, method of operating speech synthesizer and computer-readable recording medium |
WO2020256170A1 (ko) * | 2019-06-18 | 2020-12-24 | 엘지전자 주식회사 | 인공 지능을 이용한 음성 합성 장치, 음성 합성 장치의 동작 방법 및 컴퓨터로 판독 가능한 기록 매체 |
CN110442859B (zh) * | 2019-06-28 | 2023-05-26 | 中国人民解放军国防科技大学 | 标注语料生成方法、装置、设备及存储介质 |
CN110489744B (zh) * | 2019-07-25 | 2024-05-14 | 腾讯科技(深圳)有限公司 | 一种语料的处理方法、装置、电子设备和存储介质 |
CN110781660A (zh) * | 2019-10-25 | 2020-02-11 | 腾讯科技(深圳)有限公司 | 语句识别方法、装置以及计算机可读介质 |
CN111143521B (zh) * | 2019-10-28 | 2023-08-15 | 广州恒巨信息科技有限公司 | 基于知识图谱的法条检索方法、系统、装置及存储介质 |
CN110992939B (zh) * | 2019-12-18 | 2023-06-27 | 广州市百果园信息技术有限公司 | 语言模型训练方法、解码方法、装置、存储介质及设备 |
CN111125360B (zh) * | 2019-12-19 | 2023-10-20 | 网易(杭州)网络有限公司 | 游戏领域的情感分析方法、装置及其模型训练方法、装置 |
CN111291560B (zh) * | 2020-03-06 | 2023-05-23 | 深圳前海微众银行股份有限公司 | 样本扩充方法、终端、装置及可读存储介质 |
CN111507104B (zh) | 2020-03-19 | 2022-03-25 | 北京百度网讯科技有限公司 | 建立标签标注模型的方法、装置、电子设备和可读存储介质 |
CN112397054B (zh) * | 2020-12-17 | 2023-11-24 | 北京中电飞华通信有限公司 | 一种电力调度语音识别方法 |
CN112735380B (zh) * | 2020-12-28 | 2022-05-13 | 思必驰科技股份有限公司 | 重打分语言模型的打分方法及语音识别方法 |
KR102705602B1 (ko) * | 2021-05-06 | 2024-09-11 | 주식회사 카카오엔터프라이즈 | 언어 모델 생성 방법 및 장치 |
CN113177109B (zh) * | 2021-05-27 | 2024-07-16 | 中国平安人寿保险股份有限公司 | 文本的弱标注方法、装置、设备以及存储介质 |
CN116612750A (zh) * | 2023-05-23 | 2023-08-18 | 苏州科帕特信息科技有限公司 | 一种语言模型自动训练方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1168301A1 (en) * | 2000-06-28 | 2002-01-02 | Matsushita Electric Industrial Co., Ltd. | Training of acoustic models for noise robustness |
EP1528639A1 (de) * | 2003-10-29 | 2005-05-04 | Yazaki Europe Ltd. | Steckverbindergehäuse mit Kurzschlussbrücke |
CN101261832A (zh) * | 2008-04-21 | 2008-09-10 | 北京航空航天大学 | 汉语语音情感信息的提取及建模方法 |
CN102543080A (zh) * | 2010-12-24 | 2012-07-04 | 索尼公司 | 音频编辑系统和音频编辑方法 |
CN102568477A (zh) * | 2010-12-29 | 2012-07-11 | 盛乐信息技术(上海)有限公司 | 一种半监督的发音模型建模系统及方法 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6404925B1 (en) * | 1999-03-11 | 2002-06-11 | Fuji Xerox Co., Ltd. | Methods and apparatuses for segmenting an audio-visual recording using image similarity searching and audio speaker recognition |
CN1141697C (zh) * | 2000-09-27 | 2004-03-10 | 中国科学院自动化研究所 | 一种带调三音子模型及训练方法 |
JP3696231B2 (ja) * | 2002-10-08 | 2005-09-14 | 松下電器産業株式会社 | 言語モデル生成蓄積装置、音声認識装置、言語モデル生成方法および音声認識方法 |
US7684987B2 (en) * | 2004-01-21 | 2010-03-23 | Microsoft Corporation | Segmental tonal modeling for tonal languages |
FR2892846A1 (fr) * | 2005-11-03 | 2007-05-04 | France Telecom | Procede et dispositif de calcul de mesure de similarite entre une representation d'un segment audio de reference et une representation d'un segment audio a tester et procede et dispositif de suivi d'un locuteur de reference |
TWI297487B (en) * | 2005-11-18 | 2008-06-01 | Tze Fen Li | A method for speech recognition |
JPWO2007138875A1 (ja) * | 2006-05-31 | 2009-10-01 | 日本電気株式会社 | 音声認識用単語辞書・言語モデル作成システム、方法、プログラムおよび音声認識システム |
CN101346758B (zh) * | 2006-06-23 | 2011-07-27 | 松下电器产业株式会社 | 感情识别装置 |
US7617103B2 (en) * | 2006-08-25 | 2009-11-10 | Microsoft Corporation | Incrementally regulated discriminative margins in MCE training for speech recognition |
TWI389100B (zh) * | 2008-11-19 | 2013-03-11 | Inst Information Industry | 語音情緒的分類方法及其情緒語意模型的建立方法 |
CN102651217A (zh) * | 2011-02-25 | 2012-08-29 | 株式会社东芝 | 用于合成语音的方法、设备以及用于语音合成的声学模型训练方法 |
-
2013
- 2013-02-01 CN CN201310040085.1A patent/CN103971677B/zh active Active
- 2013-10-25 CA CA2899532A patent/CA2899532C/en active Active
- 2013-10-25 BR BR112015018205-4A patent/BR112015018205B1/pt active IP Right Grant
- 2013-10-25 JP JP2015555551A patent/JP5901001B1/ja active Active
- 2013-10-25 WO PCT/CN2013/085948 patent/WO2014117548A1/en active Application Filing
-
2014
- 2014-01-07 TW TW103100469A patent/TWI512719B/zh active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1168301A1 (en) * | 2000-06-28 | 2002-01-02 | Matsushita Electric Industrial Co., Ltd. | Training of acoustic models for noise robustness |
EP1528639A1 (de) * | 2003-10-29 | 2005-05-04 | Yazaki Europe Ltd. | Steckverbindergehäuse mit Kurzschlussbrücke |
CN101261832A (zh) * | 2008-04-21 | 2008-09-10 | 北京航空航天大学 | 汉语语音情感信息的提取及建模方法 |
CN102543080A (zh) * | 2010-12-24 | 2012-07-04 | 索尼公司 | 音频编辑系统和音频编辑方法 |
CN102568477A (zh) * | 2010-12-29 | 2012-07-11 | 盛乐信息技术(上海)有限公司 | 一种半监督的发音模型建模系统及方法 |
Also Published As
Publication number | Publication date |
---|---|
CN103971677A (zh) | 2014-08-06 |
TW201432669A (zh) | 2014-08-16 |
CA2899532A1 (en) | 2014-08-07 |
BR112015018205A2 (pt) | 2017-07-18 |
WO2014117548A1 (en) | 2014-08-07 |
TWI512719B (zh) | 2015-12-11 |
JP5901001B1 (ja) | 2016-04-06 |
JP2016513269A (ja) | 2016-05-12 |
CA2899532C (en) | 2017-09-19 |
BR112015018205B1 (pt) | 2022-02-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103971677B (zh) | 一种声学语言模型训练方法和装置 | |
CN108121700B (zh) | 一种关键词提取方法、装置及电子设备 | |
CN108304375B (zh) | 一种信息识别方法及其设备、存储介质、终端 | |
CN108460011B (zh) | 一种实体概念标注方法及系统 | |
WO2021068339A1 (zh) | 文本分类方法、装置及计算机可读存储介质 | |
CN112347778B (zh) | 关键词抽取方法、装置、终端设备及存储介质 | |
US9396723B2 (en) | Method and device for acoustic language model training | |
US20170031894A1 (en) | Systems and methods for domain-specific machine-interpretation of input data | |
US20130060769A1 (en) | System and method for identifying social media interactions | |
WO2020232898A1 (zh) | 文本分类方法、装置、电子设备及计算机非易失性可读存储介质 | |
EP1619620A1 (en) | Adaptation of Exponential Models | |
WO2021068683A1 (zh) | 正则表达式生成方法、装置、服务器及计算机可读存储介质 | |
CN107992477A (zh) | 文本主题确定方法、装置及电子设备 | |
US11790174B2 (en) | Entity recognition method and apparatus | |
CN103646112A (zh) | 利用了网络搜索的依存句法的领域自适应方法 | |
CN112395421B (zh) | 课程标签的生成方法、装置、计算机设备及介质 | |
CN107861948B (zh) | 一种标签提取方法、装置、设备和介质 | |
CN112487151B (zh) | 文案生成方法及装置、存储介质与电子设备 | |
CN111061876B (zh) | 事件舆情数据分析方法及装置 | |
CN113988057A (zh) | 基于概念抽取的标题生成方法、装置、设备及介质 | |
CN112579729A (zh) | 文档质量评价模型的训练方法、装置、电子设备和介质 | |
CN114202443A (zh) | 政策分类方法、装置、设备及存储介质 | |
TW202022635A (zh) | 自適應性調整關連搜尋詞的系統及其方法 | |
CN113157857B (zh) | 面向新闻的热点话题检测方法、装置及设备 | |
CN115129890A (zh) | 回馈数据图谱生成方法、生成设备、问答设备及冰箱 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20200821 Address after: 518057 Nanshan District science and technology zone, Guangdong, Zhejiang Province, science and technology in the Tencent Building on the 1st floor of the 35 layer Co-patentee after: TENCENT CLOUD COMPUTING (BEIJING) Co.,Ltd. Patentee after: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. Address before: Shenzhen Futian District City, Guangdong province 518044 Zhenxing Road, SEG Science Park 2 East Room 403 Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |