CN110390950B - 一种基于生成对抗网络的端到端语音增强方法 - Google Patents
一种基于生成对抗网络的端到端语音增强方法 Download PDFInfo
- Publication number
- CN110390950B CN110390950B CN201910761150.7A CN201910761150A CN110390950B CN 110390950 B CN110390950 B CN 110390950B CN 201910761150 A CN201910761150 A CN 201910761150A CN 110390950 B CN110390950 B CN 110390950B
- Authority
- CN
- China
- Prior art keywords
- generator
- training
- speech
- discriminator
- data
- 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 49
- 238000012549 training Methods 0.000 claims abstract description 105
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000013140 knowledge distillation Methods 0.000 claims abstract description 6
- 238000013459 approach Methods 0.000 claims description 5
- 230000008014 freezing Effects 0.000 claims description 4
- 238000007710 freezing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 11
- 238000001228 spectrum Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 238000010200 validation analysis Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 4
- 239000000654 additive Substances 0.000 description 3
- 230000000996 additive effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0264—Noise filtering characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electrically Operated Instructional Devices (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
Description
Claims (1)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910761150.7A CN110390950B (zh) | 2019-08-17 | 2019-08-17 | 一种基于生成对抗网络的端到端语音增强方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910761150.7A CN110390950B (zh) | 2019-08-17 | 2019-08-17 | 一种基于生成对抗网络的端到端语音增强方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110390950A CN110390950A (zh) | 2019-10-29 |
CN110390950B true CN110390950B (zh) | 2021-04-09 |
Family
ID=68289027
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910761150.7A Active CN110390950B (zh) | 2019-08-17 | 2019-08-17 | 一种基于生成对抗网络的端到端语音增强方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110390950B (zh) |
Families Citing this family (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111081266B (zh) * | 2019-12-18 | 2022-08-09 | 暗物智能科技(广州)有限公司 | 一种训练生成对抗网络、语音增强方法及系统 |
CN111145772A (zh) * | 2019-12-28 | 2020-05-12 | 广州国音智能科技有限公司 | 一种语音增强方法、系统及设备 |
CN111179962B (zh) * | 2020-01-02 | 2022-09-27 | 腾讯科技(深圳)有限公司 | 语音分离模型的训练方法、语音分离方法及装置 |
US11736899B2 (en) * | 2020-01-14 | 2023-08-22 | Nokia Technologies Oy | Training in communication systems |
CN111276132A (zh) * | 2020-02-04 | 2020-06-12 | 北京声智科技有限公司 | 一种语音处理方法、电子设备及计算机可读存储介质 |
CN111445919B (zh) * | 2020-03-13 | 2023-01-20 | 紫光展锐(重庆)科技有限公司 | 结合ai模型的语音增强方法、系统、电子设备和介质 |
CN111354374A (zh) * | 2020-03-13 | 2020-06-30 | 北京声智科技有限公司 | 语音处理方法、模型训练方法及电子设备 |
CN111599373B (zh) * | 2020-04-07 | 2023-04-18 | 云知声智能科技股份有限公司 | 一种降噪模型的压缩方法 |
CN113516990B (zh) * | 2020-04-10 | 2024-08-13 | 华为技术有限公司 | 一种语音增强方法、训练神经网络的方法以及相关设备 |
CN111564160B (zh) * | 2020-04-21 | 2022-10-18 | 重庆邮电大学 | 一种基于aewgan的语音降噪的方法 |
CN111625858B (zh) * | 2020-05-10 | 2023-04-07 | 武汉理工大学 | 一种垂直领域下的智能化多模态数据脱敏方法和装置 |
CN111627429B (zh) * | 2020-05-20 | 2022-10-14 | 浙江工业大学 | 一种基于CycleGAN的语音识别模型的防御方法及装置 |
CN112052948B (zh) * | 2020-08-19 | 2023-11-14 | 腾讯科技(深圳)有限公司 | 一种网络模型压缩方法、装置、存储介质和电子设备 |
CN112037760B (zh) | 2020-08-24 | 2022-01-07 | 北京百度网讯科技有限公司 | 语音频谱生成模型的训练方法、装置及电子设备 |
WO2022077305A1 (en) * | 2020-10-15 | 2022-04-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | Method and system for acoustic echo cancellation |
CN114512140A (zh) * | 2020-10-29 | 2022-05-17 | 阿里巴巴集团控股有限公司 | 语音增强方法、装置及设备 |
CN112541060B (zh) * | 2020-11-19 | 2021-08-13 | 中国科学院深圳先进技术研究院 | 一种基于对抗训练的端到端任务型对话学习框架和方法 |
CN112488294A (zh) * | 2020-11-20 | 2021-03-12 | 北京邮电大学 | 一种基于生成对抗网络的数据增强系统、方法和介质 |
CN112562707A (zh) * | 2020-11-30 | 2021-03-26 | 哈尔滨工程大学 | 一种单信道目标语音增强方法 |
CN112991330B (zh) * | 2021-04-19 | 2021-08-13 | 征图新视(江苏)科技股份有限公司 | 基于知识蒸馏的正样本工业缺陷检测方法 |
CN113299300B (zh) * | 2021-05-18 | 2023-09-26 | 广州大学 | 一种语音增强方法、装置及存储介质 |
CN113393854B (zh) * | 2021-05-19 | 2022-11-11 | 出门问问创新科技有限公司 | 一种语音处理方法、装置、电子设备和计算机存储介质 |
CN113555028B (zh) * | 2021-07-19 | 2024-08-02 | 首约科技(北京)有限公司 | 一种用于车联网语音降噪的处理方法 |
CN113380268A (zh) * | 2021-08-12 | 2021-09-10 | 北京世纪好未来教育科技有限公司 | 模型训练的方法、装置和语音信号的处理方法、装置 |
CN113707168A (zh) * | 2021-09-03 | 2021-11-26 | 合肥讯飞数码科技有限公司 | 一种语音增强方法、装置、设备及存储介质 |
CN114067819B (zh) * | 2021-11-22 | 2024-06-21 | 南京工程学院 | 基于跨层相似性知识蒸馏的语音增强方法 |
CN114743557A (zh) * | 2022-03-08 | 2022-07-12 | 三维通信股份有限公司 | 一种语音增强方法、系统及智能设备 |
CN115050379B (zh) * | 2022-04-24 | 2024-08-06 | 华侨大学 | 一种基于fhgan的高保真语音增强模型及其应用 |
CN114822576B (zh) * | 2022-04-30 | 2024-08-13 | 中国人民解放军总医院第一医学中心 | 基于磁共振脉冲序列噪声估计的通话系统语音增强方法 |
CN115588436A (zh) * | 2022-09-29 | 2023-01-10 | 沈阳新松机器人自动化股份有限公司 | 基于变分自编码器生成对抗网络的语音增强方法 |
GB2623110A (en) * | 2022-10-06 | 2024-04-10 | Nokia Technologies Oy | Apparatus, methods and computer programs for audio signal enhancement using a dataset |
CN115376501B (zh) * | 2022-10-26 | 2023-02-14 | 深圳市北科瑞讯信息技术有限公司 | 语音增强方法及装置、存储介质、电子设备 |
CN117765962B (zh) * | 2023-09-28 | 2024-05-24 | 青岛科技大学 | 一种海洋哺乳动物叫声数据增强方法 |
CN117577124B (zh) * | 2024-01-12 | 2024-04-16 | 京东城市(北京)数字科技有限公司 | 基于知识蒸馏的音频降噪模型的训练方法、装置及设备 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108922518A (zh) * | 2018-07-18 | 2018-11-30 | 苏州思必驰信息科技有限公司 | 语音数据扩增方法和系统 |
CN108986835A (zh) * | 2018-08-28 | 2018-12-11 | 百度在线网络技术(北京)有限公司 | 基于改进gan网络的语音去噪方法、装置、设备及介质 |
WO2019004592A1 (ko) * | 2017-06-27 | 2019-01-03 | 한양대학교 산학협력단 | 생성적 대립 망 기반의 음성 대역폭 확장기 및 확장 방법 |
CN109147810A (zh) * | 2018-09-30 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | 建立语音增强网络的方法、装置、设备和计算机存储介质 |
CN109308903A (zh) * | 2018-08-02 | 2019-02-05 | 平安科技(深圳)有限公司 | 语音模仿方法、终端设备及计算机可读存储介质 |
US20190065853A1 (en) * | 2017-08-31 | 2019-02-28 | Nec Laboratories America, Inc. | Parking lot surveillance with viewpoint invariant object recognition by synthesization and domain adaptation |
CN110059740A (zh) * | 2019-04-12 | 2019-07-26 | 杭州电子科技大学 | 一种针对嵌入式移动端的深度学习语义分割模型压缩方法 |
-
2019
- 2019-08-17 CN CN201910761150.7A patent/CN110390950B/zh active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019004592A1 (ko) * | 2017-06-27 | 2019-01-03 | 한양대학교 산학협력단 | 생성적 대립 망 기반의 음성 대역폭 확장기 및 확장 방법 |
US20190065853A1 (en) * | 2017-08-31 | 2019-02-28 | Nec Laboratories America, Inc. | Parking lot surveillance with viewpoint invariant object recognition by synthesization and domain adaptation |
CN108922518A (zh) * | 2018-07-18 | 2018-11-30 | 苏州思必驰信息科技有限公司 | 语音数据扩增方法和系统 |
CN109308903A (zh) * | 2018-08-02 | 2019-02-05 | 平安科技(深圳)有限公司 | 语音模仿方法、终端设备及计算机可读存储介质 |
CN108986835A (zh) * | 2018-08-28 | 2018-12-11 | 百度在线网络技术(北京)有限公司 | 基于改进gan网络的语音去噪方法、装置、设备及介质 |
CN109147810A (zh) * | 2018-09-30 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | 建立语音增强网络的方法、装置、设备和计算机存储介质 |
CN110059740A (zh) * | 2019-04-12 | 2019-07-26 | 杭州电子科技大学 | 一种针对嵌入式移动端的深度学习语义分割模型压缩方法 |
Non-Patent Citations (3)
Title |
---|
"A TRANSFER LEARNING AND PROGRESSIVE STACKING APPROACH TO REDUCING DEEP MODEL SIZES WITH AN APPLICATION TO SPEECH ENHANCEMENT";Sicheng Wang等;《2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)》;20170619;全文 * |
"SEGAN: Speech Enhancement Generative Adversarial Network";Santiago Pascual等;《arXiv:1703.09452v3 [cs.LG]》;20170609;全文 * |
"生成式对抗网络在语音增强方面的研究";孙成立 等;《计算机技术与发展》;20190228;第29卷(第2期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN110390950A (zh) | 2019-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110390950B (zh) | 一种基于生成对抗网络的端到端语音增强方法 | |
Zhao et al. | Monaural speech dereverberation using temporal convolutional networks with self attention | |
Su et al. | HiFi-GAN: High-fidelity denoising and dereverberation based on speech deep features in adversarial networks | |
Ravanelli et al. | Multi-task self-supervised learning for robust speech recognition | |
CN109859767B (zh) | 一种用于数字助听器的环境自适应神经网络降噪方法、系统及存储介质 | |
CN109841226B (zh) | 一种基于卷积递归神经网络的单通道实时降噪方法 | |
EP4006898A1 (en) | Voice recognition method, device, and computer-readable storage medium | |
CN111653288B (zh) | 基于条件变分自编码器的目标人语音增强方法 | |
CN108922513B (zh) | 语音区分方法、装置、计算机设备及存储介质 | |
CN111968666B (zh) | 基于深度域自适应网络的助听器语音增强方法 | |
Qin et al. | Far-Field End-to-End Text-Dependent Speaker Verification Based on Mixed Training Data with Transfer Learning and Enrollment Data Augmentation. | |
CN112581973B (zh) | 一种语音增强方法及系统 | |
CN109949821B (zh) | 一种利用cnn的u-net结构进行远场语音去混响的方法 | |
Wang et al. | A universal VAD based on jointly trained deep neural networks. | |
Bagchi et al. | Spectral feature mapping with mimic loss for robust speech recognition | |
CN112331232B (zh) | 一种结合cgan谱图去噪和双边滤波谱图增强的语音情感识别方法 | |
CN111862934A (zh) | 语音合成模型的改进方法和语音合成方法及装置 | |
CN112382301B (zh) | 基于轻量级神经网络的含噪语音性别识别方法及系统 | |
Kothapally et al. | Skipconvgan: Monaural speech dereverberation using generative adversarial networks via complex time-frequency masking | |
CN114267372A (zh) | 语音降噪方法、系统、电子设备和存储介质 | |
Bu et al. | Modeling speech structure to improve TF masks for speech enhancement and recognition | |
Li et al. | Generative adversarial networks for single channel separation of convolutive mixed speech signals | |
CN116959468A (zh) | 一种基于dcctn网络模型的语音增强方法、系统及设备 | |
Chen et al. | Leveraging heteroscedastic uncertainty in learning complex spectral mapping for single-channel speech enhancement | |
Li et al. | Adaptive speech intelligibility enhancement for far-and-near-end noise environments based on self-attention stargan |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Wu Jianfeng Inventor after: Qin Huibin Inventor after: Xu Min Inventor after: Qin Hongshuai Inventor after: Wang Zhangquan Inventor before: Wu Jianfeng Inventor before: Qin Huibin Inventor before: Qin Hongshuai |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210309 Address after: 312000 no.2016 Jiangxia Road, Yangxunqiao Town, Keqiao District, Shaoxing City, Zhejiang Province Applicant after: ZHEJIANG SHUREN College (ZHEJIANG SHUREN University) Address before: Room 137, middle building, No.2 building, Hangzhou University of Electronic Science and technology college students entrepreneurship Park, Xiasha Higher Education Park, Hangzhou City, Zhejiang Province, 310018 Applicant before: HANGZHOU PIONEER ELECTRONIC TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |