HK1219803A1 - 種語言模型的訓練方法及裝置、設備 - Google Patents
種語言模型的訓練方法及裝置、設備Info
- Publication number
- HK1219803A1 HK1219803A1 HK16107840.9A HK16107840A HK1219803A1 HK 1219803 A1 HK1219803 A1 HK 1219803A1 HK 16107840 A HK16107840 A HK 16107840A HK 1219803 A1 HK1219803 A1 HK 1219803A1
- Authority
- HK
- Hong Kong
- Prior art keywords
- language model
- training method
- training
- language
- model
- Prior art date
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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
-
- 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
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
-
- 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
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/197—Probabilistic grammars, e.g. word n-grams
-
- 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
- G10L2015/0633—Creating reference templates; Clustering using lexical or orthographic knowledge sources
-
- 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
- G10L2015/0635—Training updating or merging of old and new templates; Mean values; Weighting
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Machine Translation (AREA)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510719243.5A CN105654945B (zh) | 2015-10-29 | 2015-10-29 | 一种语言模型的训练方法及装置、设备 |
Publications (1)
Publication Number | Publication Date |
---|---|
HK1219803A1 true HK1219803A1 (zh) | 2017-04-13 |
Family
ID=56481810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
HK16107840.9A HK1219803A1 (zh) | 2015-10-29 | 2016-07-06 | 種語言模型的訓練方法及裝置、設備 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20170125013A1 (zh) |
EP (1) | EP3179473A4 (zh) |
JP (1) | JP2018502344A (zh) |
CN (1) | CN105654945B (zh) |
HK (1) | HK1219803A1 (zh) |
WO (1) | WO2017071226A1 (zh) |
Families Citing this family (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108573697B (zh) * | 2017-03-10 | 2021-06-01 | 北京搜狗科技发展有限公司 | 一种语言模型更新方法、装置及设备 |
CN107123418B (zh) * | 2017-05-09 | 2020-12-25 | 广东小天才科技有限公司 | 一种语音消息的处理方法及移动终端 |
CN107346336B (zh) * | 2017-06-29 | 2021-06-08 | 北京百度网讯科技有限公司 | 基于人工智能的信息处理方法和装置 |
CN107945792B (zh) * | 2017-11-06 | 2021-05-28 | 百度在线网络技术(北京)有限公司 | 语音处理方法和装置 |
CN109816412B (zh) * | 2017-11-21 | 2022-11-29 | 腾讯科技(深圳)有限公司 | 一种训练模型生成方法、装置、设备和计算机存储介质 |
CN110111780B (zh) * | 2018-01-31 | 2023-04-25 | 阿里巴巴集团控股有限公司 | 数据处理方法和服务器 |
CN108647200A (zh) * | 2018-04-04 | 2018-10-12 | 顺丰科技有限公司 | 对话意图分类方法及装置、设备和存储介质 |
CN108597502A (zh) * | 2018-04-27 | 2018-09-28 | 上海适享文化传播有限公司 | 基于对抗训练的领域语音识别训练方法 |
CN110472223A (zh) * | 2018-05-10 | 2019-11-19 | 北京搜狗科技发展有限公司 | 一种输入配置方法、装置和电子设备 |
CN109271495B (zh) * | 2018-08-14 | 2023-02-17 | 创新先进技术有限公司 | 问答识别效果检测方法、装置、设备及可读存储介质 |
CN109408829B (zh) * | 2018-11-09 | 2022-06-24 | 北京百度网讯科技有限公司 | 文章可读性确定方法、装置、设备和介质 |
CN110164421B (zh) | 2018-12-14 | 2022-03-11 | 腾讯科技(深圳)有限公司 | 语音解码方法、装置及存储介质 |
CN109300472A (zh) * | 2018-12-21 | 2019-02-01 | 深圳创维-Rgb电子有限公司 | 一种语音识别方法、装置、设备及介质 |
CN110349569B (zh) * | 2019-07-02 | 2022-04-15 | 思必驰科技股份有限公司 | 定制化产品语言模型的训练和识别方法及装置 |
US11710492B2 (en) * | 2019-10-02 | 2023-07-25 | Qualcomm Incorporated | Speech encoding using a pre-encoded database |
CN113012685B (zh) * | 2019-12-20 | 2022-06-07 | 北京世纪好未来教育科技有限公司 | 音频识别方法、装置、电子设备及存储介质 |
CN113096646B (zh) * | 2019-12-20 | 2022-06-07 | 北京世纪好未来教育科技有限公司 | 音频识别方法、装置、电子设备及存储介质 |
CN111161739B (zh) * | 2019-12-28 | 2023-01-17 | 科大讯飞股份有限公司 | 语音识别方法及相关产品 |
CN111143518B (zh) * | 2019-12-30 | 2021-09-07 | 北京明朝万达科技股份有限公司 | 跨领域语言模型训练方法、装置、电子设备及存储介质 |
CN111428448B (zh) * | 2020-03-02 | 2024-05-07 | 平安科技(深圳)有限公司 | 文本生成方法、装置、计算机设备及可读存储介质 |
CN111382403A (zh) * | 2020-03-17 | 2020-07-07 | 同盾控股有限公司 | 用户行为识别模型的训练方法、装置、设备及存储介质 |
CN111402864A (zh) * | 2020-03-19 | 2020-07-10 | 北京声智科技有限公司 | 语音处理方法及电子设备 |
CN111814466A (zh) * | 2020-06-24 | 2020-10-23 | 平安科技(深圳)有限公司 | 基于机器阅读理解的信息抽取方法、及其相关设备 |
CN112151021A (zh) * | 2020-09-27 | 2020-12-29 | 北京达佳互联信息技术有限公司 | 语言模型的训练方法、语音识别方法、装置及电子设备 |
CN112489646B (zh) * | 2020-11-18 | 2024-04-02 | 北京华宇信息技术有限公司 | 语音识别方法及其装置 |
CN112560451B (zh) * | 2021-02-20 | 2021-05-14 | 京华信息科技股份有限公司 | 一种自动生成训练数据的错别字校对方法及装置 |
CN113657461A (zh) * | 2021-07-28 | 2021-11-16 | 北京宝兰德软件股份有限公司 | 基于文本分类的日志异常检测方法、系统、设备及介质 |
CN113744723B (zh) * | 2021-10-13 | 2024-01-30 | 浙江核新同花顺网络信息股份有限公司 | 一种语音识别实时重打分的方法和系统 |
CN114141236B (zh) * | 2021-10-28 | 2023-01-06 | 北京百度网讯科技有限公司 | 语言模型更新方法、装置、电子设备及存储介质 |
CN113782001B (zh) * | 2021-11-12 | 2022-03-08 | 深圳市北科瑞声科技股份有限公司 | 一种特定领域语音识别方法、装置、电子设备及存储介质 |
CN113889085A (zh) * | 2021-11-22 | 2022-01-04 | 北京百度网讯科技有限公司 | 语音识别方法、装置、设备、存储介质及程序产品 |
CN117407242B (zh) * | 2023-10-10 | 2024-04-05 | 浙江大学 | 基于大语言模型的低成本、零样本的在线日志解析方法 |
Family Cites Families (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6477488B1 (en) * | 2000-03-10 | 2002-11-05 | Apple Computer, Inc. | Method for dynamic context scope selection in hybrid n-gram+LSA language modeling |
JP2003255985A (ja) * | 2002-02-28 | 2003-09-10 | Toshiba Corp | 統計的言語モデル作成方法及び装置並びにプログラム |
DE60316912T2 (de) * | 2003-04-29 | 2008-07-31 | Sony Deutschland Gmbh | Verfahren zur Spracherkennung |
US8301448B2 (en) * | 2006-03-29 | 2012-10-30 | Nuance Communications, Inc. | System and method for applying dynamic contextual grammars and language models to improve automatic speech recognition accuracy |
US7756708B2 (en) * | 2006-04-03 | 2010-07-13 | Google Inc. | Automatic language model update |
WO2008001485A1 (fr) * | 2006-06-26 | 2008-01-03 | Nec Corporation | système de génération de modèles de langue, procédé de génération de modèles de langue et programme de génération de modèles de langue |
WO2008004663A1 (fr) * | 2006-07-07 | 2008-01-10 | Nec Corporation | Dispositif de mise à jour de modèle de langage, procédé de mise à jour de modèle de langage, et programme de mise à jour de modèle de langage |
US8972268B2 (en) * | 2008-04-15 | 2015-03-03 | Facebook, Inc. | Enhanced speech-to-speech translation system and methods for adding a new word |
CN101271450B (zh) * | 2007-03-19 | 2010-09-29 | 株式会社东芝 | 裁剪语言模型的方法及装置 |
US8682660B1 (en) * | 2008-05-21 | 2014-03-25 | Resolvity, Inc. | Method and system for post-processing speech recognition results |
JP4928514B2 (ja) * | 2008-08-27 | 2012-05-09 | 日本放送協会 | 音声認識装置及び音声認識プログラム |
CN102280106A (zh) * | 2010-06-12 | 2011-12-14 | 三星电子株式会社 | 用于移动通信终端的语音网络搜索方法及其装置 |
US8938391B2 (en) * | 2011-06-12 | 2015-01-20 | Microsoft Corporation | Dynamically adding personalization features to language models for voice search |
JP2013050605A (ja) * | 2011-08-31 | 2013-03-14 | Nippon Hoso Kyokai <Nhk> | 言語モデル切替装置およびそのプログラム |
CN103164198A (zh) * | 2011-12-14 | 2013-06-19 | 深圳市腾讯计算机系统有限公司 | 一种裁减语言模型的方法和装置 |
US9009025B1 (en) * | 2011-12-27 | 2015-04-14 | Amazon Technologies, Inc. | Context-based utterance recognition |
CN103187052B (zh) * | 2011-12-29 | 2015-09-02 | 北京百度网讯科技有限公司 | 一种建立用于语音识别的语言模型的方法及装置 |
CN102623010B (zh) * | 2012-02-29 | 2015-09-02 | 北京百度网讯科技有限公司 | 一种建立语言模型的方法、语音识别的方法及其装置 |
CN102722525A (zh) * | 2012-05-15 | 2012-10-10 | 北京百度网讯科技有限公司 | 通讯录人名的语言模型建立方法、语音搜索方法及其系统 |
US9043205B2 (en) * | 2012-06-21 | 2015-05-26 | Google Inc. | Dynamic language model |
US9047868B1 (en) * | 2012-07-31 | 2015-06-02 | Amazon Technologies, Inc. | Language model data collection |
CN103680498A (zh) * | 2012-09-26 | 2014-03-26 | 华为技术有限公司 | 一种语音识别方法和设备 |
US9035884B2 (en) * | 2012-10-17 | 2015-05-19 | Nuance Communications, Inc. | Subscription updates in multiple device language models |
US8589164B1 (en) * | 2012-10-18 | 2013-11-19 | Google Inc. | Methods and systems for speech recognition processing using search query information |
CN103871402B (zh) * | 2012-12-11 | 2017-10-10 | 北京百度网讯科技有限公司 | 语言模型训练系统、语音识别系统及相应方法 |
CN103871403B (zh) * | 2012-12-13 | 2017-04-12 | 北京百度网讯科技有限公司 | 建立语音识别模型的方法、语音识别方法及对应装置 |
CN103971675B (zh) * | 2013-01-29 | 2016-03-02 | 腾讯科技(深圳)有限公司 | 自动语音识别方法和系统 |
CN103971677B (zh) * | 2013-02-01 | 2015-08-12 | 腾讯科技(深圳)有限公司 | 一种声学语言模型训练方法和装置 |
US9484023B2 (en) * | 2013-02-22 | 2016-11-01 | International Business Machines Corporation | Conversion of non-back-off language models for efficient speech decoding |
CN104217717B (zh) * | 2013-05-29 | 2016-11-23 | 腾讯科技(深圳)有限公司 | 构建语言模型的方法及装置 |
CN103456300B (zh) * | 2013-08-07 | 2016-04-20 | 科大讯飞股份有限公司 | 一种基于class-base语言模型的POI语音识别方法 |
CN103810999B (zh) * | 2014-02-27 | 2016-10-19 | 清华大学 | 基于分布式神经网络的语言模型训练方法及其系统 |
US9412365B2 (en) * | 2014-03-24 | 2016-08-09 | Google Inc. | Enhanced maximum entropy models |
JP5932869B2 (ja) * | 2014-03-27 | 2016-06-08 | インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation | N−gram言語モデルの教師無し学習方法、学習装置、および学習プログラム |
CN104572631B (zh) * | 2014-12-03 | 2018-04-13 | 北京捷通华声语音技术有限公司 | 一种语言模型的训练方法及系统 |
CN104572614A (zh) * | 2014-12-03 | 2015-04-29 | 北京捷通华声语音技术有限公司 | 一种语言模型的训练方法及系统 |
-
2015
- 2015-10-29 CN CN201510719243.5A patent/CN105654945B/zh active Active
-
2016
- 2016-06-06 EP EP16762948.4A patent/EP3179473A4/en not_active Withdrawn
- 2016-06-06 WO PCT/CN2016/084959 patent/WO2017071226A1/zh active Application Filing
- 2016-06-06 JP JP2016564631A patent/JP2018502344A/ja active Pending
- 2016-07-06 HK HK16107840.9A patent/HK1219803A1/zh unknown
- 2016-08-19 US US15/242,065 patent/US20170125013A1/en not_active Abandoned
Also Published As
Publication number | Publication date |
---|---|
CN105654945B (zh) | 2020-03-06 |
JP2018502344A (ja) | 2018-01-25 |
WO2017071226A1 (zh) | 2017-05-04 |
EP3179473A1 (en) | 2017-06-14 |
EP3179473A4 (en) | 2017-07-12 |
US20170125013A1 (en) | 2017-05-04 |
CN105654945A (zh) | 2016-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
HK1219803A1 (zh) | 種語言模型的訓練方法及裝置、設備 | |
SG11202000749RA (en) | Model training method and apparatus | |
SG11202001040TA (en) | Method, apparatus, and device for training risk control model and risk control | |
IL246798A0 (en) | Inhalation training device and system for practicing the inhalation process of a patient | |
HK1199672A1 (zh) | 種聲學模型訓練方法和裝置 | |
PT3209393T (pt) | Dispositivo de exercício de remo e método de uso do mesmo | |
GB201916397D0 (en) | Method and apparatus for facilitating creation of simulation model | |
EP3451206C0 (en) | METHOD, DEVICE AND PROGRAM FOR GENERATING A SIMULATION MODEL OF A ROOM | |
SG11201701806WA (en) | A method and apparatus to control a mode of a device | |
GB201708974D0 (en) | Method and apparatus for executing a scripting language | |
GB201815539D0 (en) | Method and apparatus for deriving a set of training data | |
GB201705665D0 (en) | A system and method for training use of a toothbrush | |
GB2542065B (en) | An exercise device and method of exercising using said device | |
GB201704807D0 (en) | Exercise class apparatus and method | |
GB2539574B (en) | An exercise device and method of exercising using said device | |
EP3140015A4 (en) | Core muscle training apparatus and method | |
GB201511299D0 (en) | Test device and method of using a test device | |
GB201515606D0 (en) | Apparatus and method for training a swimmer | |
HK1220833A1 (zh) | 減少靈活的解析器中的延遲的方法及其裝置 | |
GB2534180B (en) | An apparatus and method for applying forces to a pelvis of a person | |
IL262764A (en) | Training system and a method of using same | |
HK1256019B (zh) | 訓練設備和方法 | |
HK1220835A1 (zh) | 使用通用修改指令來實現分組的靈活修改的方法及其裝置 | |
GB201700882D0 (en) | A training device and method of training | |
GB201700156D0 (en) | A training device and method of training |