CN110556100B - 端到端语音识别模型的训练方法及系统 - Google Patents
端到端语音识别模型的训练方法及系统 Download PDFInfo
- Publication number
- CN110556100B CN110556100B CN201910853470.5A CN201910853470A CN110556100B CN 110556100 B CN110556100 B CN 110556100B CN 201910853470 A CN201910853470 A CN 201910853470A CN 110556100 B CN110556100 B CN 110556100B
- Authority
- CN
- China
- Prior art keywords
- model
- training
- speech recognition
- acoustic
- acoustic 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.)
- Active
Links
- 238000012549 training Methods 0.000 title claims abstract description 124
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000004590 computer program Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 abstract description 5
- 238000002474 experimental method Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 230000006872 improvement Effects 0.000 description 9
- 238000005070 sampling Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 8
- 102000029791 ADAM Human genes 0.000 description 7
- 108091022885 ADAM Proteins 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 6
- 238000013459 approach Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000005266 circulating tumour cell Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002864 sequence alignment Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
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 (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910853470.5A CN110556100B (zh) | 2019-09-10 | 2019-09-10 | 端到端语音识别模型的训练方法及系统 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910853470.5A CN110556100B (zh) | 2019-09-10 | 2019-09-10 | 端到端语音识别模型的训练方法及系统 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110556100A CN110556100A (zh) | 2019-12-10 |
CN110556100B true CN110556100B (zh) | 2021-09-17 |
Family
ID=68739590
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910853470.5A Active CN110556100B (zh) | 2019-09-10 | 2019-09-10 | 端到端语音识别模型的训练方法及系统 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110556100B (zh) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110930980B (zh) * | 2019-12-12 | 2022-08-05 | 思必驰科技股份有限公司 | 一种中英文混合语音的声学识别方法及系统 |
CN110970031B (zh) * | 2019-12-16 | 2022-06-24 | 思必驰科技股份有限公司 | 语音识别系统及方法 |
CN113192496A (zh) * | 2020-01-10 | 2021-07-30 | 普天信息技术有限公司 | 语音识别方法及装置 |
CN111275170B (zh) * | 2020-01-19 | 2023-11-24 | 腾讯科技(深圳)有限公司 | 一种模型训练方法和相关装置 |
CN111179918B (zh) * | 2020-02-20 | 2022-10-14 | 中国科学院声学研究所 | 联结主义时间分类和截断式注意力联合在线语音识别技术 |
CN111354345B (zh) * | 2020-03-11 | 2021-08-31 | 北京字节跳动网络技术有限公司 | 生成语音模型和语音识别的方法、装置、设备以及介质 |
CN111681646A (zh) * | 2020-07-17 | 2020-09-18 | 成都三零凯天通信实业有限公司 | 端到端架构的通用场景中文普通话语音识别方法 |
CN112185352B (zh) * | 2020-08-31 | 2024-05-17 | 华为技术有限公司 | 语音识别方法、装置及电子设备 |
CN112349288A (zh) * | 2020-09-18 | 2021-02-09 | 昆明理工大学 | 基于拼音约束联合学习的汉语语音识别方法 |
US11615782B2 (en) * | 2020-11-12 | 2023-03-28 | Sony Interactive Entertainment Inc. | Semi-sorted batching with variable length input for efficient training |
CN112599116B (zh) * | 2020-12-25 | 2022-07-08 | 思必驰科技股份有限公司 | 语音识别模型训练方法和语音识别联邦训练系统 |
US11908458B2 (en) | 2020-12-29 | 2024-02-20 | International Business Machines Corporation | Customization of recurrent neural network transducers for speech recognition |
CN112967710B (zh) * | 2021-03-25 | 2022-06-14 | 江西师范大学 | 一种低资源客家方言点识别方法 |
CN113223506B (zh) * | 2021-05-28 | 2022-05-20 | 思必驰科技股份有限公司 | 语音识别模型训练方法及语音识别方法 |
CN113539244B (zh) * | 2021-07-22 | 2023-10-03 | 广州虎牙科技有限公司 | 端到端语音识别模型训练方法、语音识别方法及相关装置 |
CN117079646B (zh) * | 2023-10-13 | 2024-01-09 | 之江实验室 | 一种语音识别模型的训练方法、装置、设备及存储介质 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108269568A (zh) * | 2017-01-03 | 2018-07-10 | 中国科学院声学研究所 | 一种基于ctc的声学模型训练方法 |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7574358B2 (en) * | 2005-02-28 | 2009-08-11 | International Business Machines Corporation | Natural language system and method based on unisolated performance metric |
US8571857B2 (en) * | 2010-10-20 | 2013-10-29 | At&T Intellectual Property I, L.P. | System and method for generating models for use in automatic speech recognition |
US9786270B2 (en) * | 2015-07-09 | 2017-10-10 | Google Inc. | Generating acoustic models |
CN106328122A (zh) * | 2016-08-19 | 2017-01-11 | 深圳市唯特视科技有限公司 | 一种利用长短期记忆模型递归神经网络的语音识别方法 |
CN107808660A (zh) * | 2016-09-05 | 2018-03-16 | 株式会社东芝 | 训练神经网络语言模型的方法和装置及语音识别方法和装置 |
US11081105B2 (en) * | 2016-09-16 | 2021-08-03 | Nippon Telegraph And Telephone Corporation | Model learning device, method and recording medium for learning neural network model |
KR102399535B1 (ko) * | 2017-03-23 | 2022-05-19 | 삼성전자주식회사 | 음성 인식을 위한 학습 방법 및 장치 |
US20190130896A1 (en) * | 2017-10-26 | 2019-05-02 | Salesforce.Com, Inc. | Regularization Techniques for End-To-End Speech Recognition |
US10971142B2 (en) * | 2017-10-27 | 2021-04-06 | Baidu Usa Llc | Systems and methods for robust speech recognition using generative adversarial networks |
US11776530B2 (en) * | 2017-11-15 | 2023-10-03 | Intel Corporation | Speech model personalization via ambient context harvesting |
US10672388B2 (en) * | 2017-12-15 | 2020-06-02 | Mitsubishi Electric Research Laboratories, Inc. | Method and apparatus for open-vocabulary end-to-end speech recognition |
CN108417202B (zh) * | 2018-01-19 | 2020-09-01 | 苏州思必驰信息科技有限公司 | 语音识别方法及系统 |
CN108962224B (zh) * | 2018-07-19 | 2020-06-26 | 苏州思必驰信息科技有限公司 | 口语理解和语言模型联合建模方法、对话方法及系统 |
CN109346064B (zh) * | 2018-12-13 | 2021-07-27 | 思必驰科技股份有限公司 | 用于端到端语音识别模型的训练方法及系统 |
CN109949796B (zh) * | 2019-02-28 | 2021-04-06 | 天津大学 | 一种基于藏文部件的端到端架构拉萨方言语音识别方法 |
-
2019
- 2019-09-10 CN CN201910853470.5A patent/CN110556100B/zh active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108269568A (zh) * | 2017-01-03 | 2018-07-10 | 中国科学院声学研究所 | 一种基于ctc的声学模型训练方法 |
Non-Patent Citations (2)
Title |
---|
End-to-end Monaural Multi-speaker ASR System without Pretraining;Xuankai Chang;《ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)》;20190417;6256-6260 * |
端到端自动语音识别技术研究;蒋竺芳;《中国优秀硕士学位论文全文数据库信息科技辑》;20190831;I136-100 * |
Also Published As
Publication number | Publication date |
---|---|
CN110556100A (zh) | 2019-12-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110556100B (zh) | 端到端语音识别模型的训练方法及系统 | |
US11900915B2 (en) | Multi-dialect and multilingual speech recognition | |
US11335333B2 (en) | Speech recognition with sequence-to-sequence models | |
US11837216B2 (en) | Speech recognition using unspoken text and speech synthesis | |
US9786270B2 (en) | Generating acoustic models | |
Le et al. | Deep shallow fusion for RNN-T personalization | |
US20200027444A1 (en) | Speech recognition with sequence-to-sequence models | |
US11222627B1 (en) | Exploring ASR-free end-to-end modeling to improve spoken language understanding in a cloud-based dialog system | |
US10867597B2 (en) | Assignment of semantic labels to a sequence of words using neural network architectures | |
CN113811946A (zh) | 数字序列的端到端自动语音识别 | |
JP7055630B2 (ja) | 音声認識のための学習方法、学習装置、コンピュータプログラム及び記憶媒体 | |
JP2023545988A (ja) | トランスフォーマトランスデューサ:ストリーミング音声認識と非ストリーミング音声認識を統合する1つのモデル | |
Yu et al. | Deep neural network-hidden markov model hybrid systems | |
Rasipuram et al. | Acoustic and lexical resource constrained ASR using language-independent acoustic model and language-dependent probabilistic lexical model | |
CN118043885A (zh) | 用于半监督语音识别的对比孪生网络 | |
McGraw et al. | Automating Crowd-supervised Learning for Spoken Language Systems. | |
Qian et al. | Spoken language understanding of human-machine conversations for language learning applications | |
Li et al. | Semi-supervised ensemble DNN acoustic model training | |
Razavi et al. | Acoustic data-driven grapheme-to-phoneme conversion in the probabilistic lexical modeling framework | |
Bataev et al. | Exploring end-to-end techniques for low-resource speech recognition | |
CN111462734B (zh) | 语义槽填充模型训练方法及系统 | |
Ponting | Computational Models of Speech Pattern Processing | |
Rasipuram | Probabilistic lexical modeling and grapheme-based automatic speech recognition | |
Evrard | Transformers in automatic speech recognition | |
Kheddar et al. | Automatic speech recognition using advanced deep learning approaches: A survey |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200616 Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant after: AI SPEECH Ltd. Applicant after: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant before: AI SPEECH Ltd. Applicant before: SHANGHAI JIAO TONG University |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201026 Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant after: AI SPEECH Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant before: AI SPEECH Ltd. Applicant before: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. |
|
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant before: AI SPEECH Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |