CN110085215A - 一种基于生成对抗网络的语言模型数据增强方法 - Google Patents
一种基于生成对抗网络的语言模型数据增强方法 Download PDFInfo
- Publication number
- CN110085215A CN110085215A CN201810064982.9A CN201810064982A CN110085215A CN 110085215 A CN110085215 A CN 110085215A CN 201810064982 A CN201810064982 A CN 201810064982A CN 110085215 A CN110085215 A CN 110085215A
- Authority
- CN
- China
- Prior art keywords
- model
- sequence
- sample
- training
- language model
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 62
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 20
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 4
- 210000004218 nerve net Anatomy 0.000 claims 1
- 230000002708 enhancing effect Effects 0.000 description 6
- 238000005070 sampling Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 241001672694 Citrus reticulata Species 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 description 1
- 101100389815 Caenorhabditis elegans eva-1 gene Proteins 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 101150049349 setA gene Proteins 0.000 description 1
- 238000012360 testing method Methods 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
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (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)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
Description
Claims (7)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810064982.9A CN110085215B (zh) | 2018-01-23 | 2018-01-23 | 一种基于生成对抗网络的语言模型数据增强方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810064982.9A CN110085215B (zh) | 2018-01-23 | 2018-01-23 | 一种基于生成对抗网络的语言模型数据增强方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110085215A true CN110085215A (zh) | 2019-08-02 |
CN110085215B CN110085215B (zh) | 2021-06-08 |
Family
ID=67411927
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810064982.9A Active CN110085215B (zh) | 2018-01-23 | 2018-01-23 | 一种基于生成对抗网络的语言模型数据增强方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110085215B (zh) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110808057A (zh) * | 2019-10-31 | 2020-02-18 | 南昌航空大学 | 一种基于约束朴素生成对抗网络的语音增强方法 |
CN111798874A (zh) * | 2020-06-24 | 2020-10-20 | 西北师范大学 | 一种语音情绪识别方法及系统 |
CN112133326A (zh) * | 2020-09-08 | 2020-12-25 | 东南大学 | 一种基于对抗神经网络的枪声数据增广与检测方法 |
CN112420050A (zh) * | 2020-11-18 | 2021-02-26 | 北京帝派智能科技有限公司 | 一种语音识别方法、装置和电子设备 |
CN112599121A (zh) * | 2020-12-03 | 2021-04-02 | 天津大学 | 基于辅助数据正则化的说话人自适应方法 |
CN112800111A (zh) * | 2021-01-26 | 2021-05-14 | 重庆邮电大学 | 一种基于训练数据挖掘的位置预测方法 |
CN113066483A (zh) * | 2019-12-31 | 2021-07-02 | 南昌航空大学 | 一种基于稀疏连续约束的生成对抗网络语音增强方法 |
WO2021139250A1 (zh) * | 2020-07-31 | 2021-07-15 | 平安科技(深圳)有限公司 | 一种数据增强模型的训练方法及装置 |
CN113642341A (zh) * | 2021-06-30 | 2021-11-12 | 深译信息科技(横琴)有限公司 | 一种解决医学文本数据稀缺性的深度对抗生成方法 |
CN114844767A (zh) * | 2022-04-27 | 2022-08-02 | 中国电子科技集团公司第五十四研究所 | 一种基于对抗生成网络的告警数据生成方法 |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040186714A1 (en) * | 2003-03-18 | 2004-09-23 | Aurilab, Llc | Speech recognition improvement through post-processsing |
US20060277033A1 (en) * | 2005-06-01 | 2006-12-07 | Microsoft Corporation | Discriminative training for language modeling |
CN101154221A (zh) * | 2006-09-28 | 2008-04-02 | 株式会社东芝 | 执行输入语音翻译处理的装置 |
JP2008225907A (ja) * | 2007-03-13 | 2008-09-25 | Nippon Telegr & Teleph Corp <Ntt> | 言語解析モデル学習装置、言語解析モデル学習方法、言語解析モデル学習プログラムならびにその記録媒体 |
US20090271002A1 (en) * | 2008-04-29 | 2009-10-29 | David Asofsky | System and Method for Remotely Controlling Electronic Devices |
US20120278060A1 (en) * | 2011-04-27 | 2012-11-01 | Xerox Corporation | Method and system for confidence-weighted learning of factored discriminative language models |
KR20130126794A (ko) * | 2012-04-19 | 2013-11-21 | 금오공과대학교 산학협력단 | 오디오 녹음 기기 판별 시스템 및 그 판별 방법 |
CN103843061A (zh) * | 2011-07-29 | 2014-06-04 | 三星电子株式会社 | 音频信号处理方法及其音频信号处理设备 |
CN105654954A (zh) * | 2016-04-06 | 2016-06-08 | 普强信息技术(北京)有限公司 | 一种云端语音识别系统及方法 |
US9471566B1 (en) * | 2005-04-14 | 2016-10-18 | Oracle America, Inc. | Method and apparatus for converting phonetic language input to written language output |
CN107293289A (zh) * | 2017-06-13 | 2017-10-24 | 南京医科大学 | 一种基于深度卷积生成对抗网络的语音生成方法 |
CN107330444A (zh) * | 2017-05-27 | 2017-11-07 | 苏州科技大学 | 一种基于生成对抗网络的图像自动文本标注方法 |
-
2018
- 2018-01-23 CN CN201810064982.9A patent/CN110085215B/zh active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040186714A1 (en) * | 2003-03-18 | 2004-09-23 | Aurilab, Llc | Speech recognition improvement through post-processsing |
US9471566B1 (en) * | 2005-04-14 | 2016-10-18 | Oracle America, Inc. | Method and apparatus for converting phonetic language input to written language output |
US20060277033A1 (en) * | 2005-06-01 | 2006-12-07 | Microsoft Corporation | Discriminative training for language modeling |
CN101154221A (zh) * | 2006-09-28 | 2008-04-02 | 株式会社东芝 | 执行输入语音翻译处理的装置 |
JP2008225907A (ja) * | 2007-03-13 | 2008-09-25 | Nippon Telegr & Teleph Corp <Ntt> | 言語解析モデル学習装置、言語解析モデル学習方法、言語解析モデル学習プログラムならびにその記録媒体 |
US20090271002A1 (en) * | 2008-04-29 | 2009-10-29 | David Asofsky | System and Method for Remotely Controlling Electronic Devices |
US20120278060A1 (en) * | 2011-04-27 | 2012-11-01 | Xerox Corporation | Method and system for confidence-weighted learning of factored discriminative language models |
CN103843061A (zh) * | 2011-07-29 | 2014-06-04 | 三星电子株式会社 | 音频信号处理方法及其音频信号处理设备 |
KR20130126794A (ko) * | 2012-04-19 | 2013-11-21 | 금오공과대학교 산학협력단 | 오디오 녹음 기기 판별 시스템 및 그 판별 방법 |
CN105654954A (zh) * | 2016-04-06 | 2016-06-08 | 普强信息技术(北京)有限公司 | 一种云端语音识别系统及方法 |
CN107330444A (zh) * | 2017-05-27 | 2017-11-07 | 苏州科技大学 | 一种基于生成对抗网络的图像自动文本标注方法 |
CN107293289A (zh) * | 2017-06-13 | 2017-10-24 | 南京医科大学 | 一种基于深度卷积生成对抗网络的语音生成方法 |
Non-Patent Citations (5)
Title |
---|
EMILY DENTON ET AL.: "Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks", 《ICLA》 * |
LYNDA SAID LHADJ ET AL.: "Enhancing information retrieval through concept‐based language modeling and semantic smoothing", 《JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY》 * |
PARIKH, ANKUR P. , ET AL: "Language Modeling with Power Low Rank Ensembles", 《COMPUTER SCIENCE》 * |
YIKE ZHANG ET AL.: "Improving Language Modeling with an Adversarial Critic for Automatic Speech Recognition", 《INTERSPEECH》 * |
张一珂 等: "基于对抗训练策略的语言模型数据增强技术", 《自动化学报》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110808057A (zh) * | 2019-10-31 | 2020-02-18 | 南昌航空大学 | 一种基于约束朴素生成对抗网络的语音增强方法 |
CN113066483A (zh) * | 2019-12-31 | 2021-07-02 | 南昌航空大学 | 一种基于稀疏连续约束的生成对抗网络语音增强方法 |
CN113066483B (zh) * | 2019-12-31 | 2024-01-30 | 广州航海学院 | 一种基于稀疏连续约束的生成对抗网络语音增强方法 |
CN111798874A (zh) * | 2020-06-24 | 2020-10-20 | 西北师范大学 | 一种语音情绪识别方法及系统 |
WO2021139250A1 (zh) * | 2020-07-31 | 2021-07-15 | 平安科技(深圳)有限公司 | 一种数据增强模型的训练方法及装置 |
CN112133326A (zh) * | 2020-09-08 | 2020-12-25 | 东南大学 | 一种基于对抗神经网络的枪声数据增广与检测方法 |
CN112420050A (zh) * | 2020-11-18 | 2021-02-26 | 北京帝派智能科技有限公司 | 一种语音识别方法、装置和电子设备 |
CN112420050B (zh) * | 2020-11-18 | 2021-06-18 | 北京帝派智能科技有限公司 | 一种语音识别方法、装置和电子设备 |
CN112599121A (zh) * | 2020-12-03 | 2021-04-02 | 天津大学 | 基于辅助数据正则化的说话人自适应方法 |
CN112800111A (zh) * | 2021-01-26 | 2021-05-14 | 重庆邮电大学 | 一种基于训练数据挖掘的位置预测方法 |
CN113642341A (zh) * | 2021-06-30 | 2021-11-12 | 深译信息科技(横琴)有限公司 | 一种解决医学文本数据稀缺性的深度对抗生成方法 |
CN114844767A (zh) * | 2022-04-27 | 2022-08-02 | 中国电子科技集团公司第五十四研究所 | 一种基于对抗生成网络的告警数据生成方法 |
Also Published As
Publication number | Publication date |
---|---|
CN110085215B (zh) | 2021-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110085215A (zh) | 一种基于生成对抗网络的语言模型数据增强方法 | |
CN110210029B (zh) | 基于垂直领域的语音文本纠错方法、系统、设备及介质 | |
CN111241294B (zh) | 基于依赖解析和关键词的图卷积网络的关系抽取方法 | |
JP6444530B2 (ja) | 音声言語理解システム | |
CN108763504B (zh) | 一种基于强化双通道序列学习的对话回复生成方法及系统 | |
CN107943784B (zh) | 基于生成对抗网络的关系抽取方法 | |
CN107273913B (zh) | 一种基于多特征融合的短文本相似度计算方法 | |
CN112417894B (zh) | 一种基于多任务学习的对话意图识别方法及识别系统 | |
CN108475262A (zh) | 用于文本处理的电子设备和方法 | |
CN106980609A (zh) | 一种基于词向量表示的条件随机场的命名实体识别方法 | |
CN111125333B (zh) | 一种基于表示学习与多层覆盖机制的生成式知识问答方法 | |
CN104156349B (zh) | 基于统计词典模型的未登录词发现和分词系统及方法 | |
CN112232087B (zh) | 一种基于Transformer的多粒度注意力模型的特定方面情感分析方法 | |
CN110516240B (zh) | 一种基于Transformer的语义相似度计算模型DSSM技术 | |
CN113822054A (zh) | 基于数据增强的中文语法纠错方法及装置 | |
CN113435211A (zh) | 一种结合外部知识的文本隐式情感分析方法 | |
Wu et al. | A probabilistic framework for representing dialog systems and entropy-based dialog management through dynamic stochastic state evolution | |
CN109543036A (zh) | 基于语义相似度的文本聚类方法 | |
Puigcerver et al. | Probabilistic interpretation and improvements to the HMM-filler for handwritten keyword spotting | |
Wang et al. | Improving handwritten Chinese text recognition by unsupervised language model adaptation | |
CN115952284A (zh) | 一种融合密度聚类与ernie的医疗文本关系抽取方法 | |
Mamatov et al. | Construction of language models for Uzbek language | |
CN115376547A (zh) | 发音评测方法、装置、计算机设备和存储介质 | |
CN114896966A (zh) | 一种中文文本语法错误定位方法、系统、设备及介质 | |
CN108563639B (zh) | 一种基于循环神经网络的蒙古语语言模型 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20241010 Address after: 100190, No. 21 West Fourth Ring Road, Beijing, Haidian District Patentee after: INSTITUTE OF ACOUSTICS, CHINESE ACADEMY OF SCIENCES Country or region after: China Address before: 100190, No. 21 West Fourth Ring Road, Beijing, Haidian District Patentee before: INSTITUTE OF ACOUSTICS, CHINESE ACADEMY OF SCIENCES Country or region before: China Patentee before: BEIJING KEXIN TECHNOLOGY Co.,Ltd. |