CN101814159A - 基于自联想神经网络和高斯混合背景模型相结合的说话人确认方法 - Google Patents
基于自联想神经网络和高斯混合背景模型相结合的说话人确认方法 Download PDFInfo
- Publication number
- CN101814159A CN101814159A CN200910024432A CN200910024432A CN101814159A CN 101814159 A CN101814159 A CN 101814159A CN 200910024432 A CN200910024432 A CN 200910024432A CN 200910024432 A CN200910024432 A CN 200910024432A CN 101814159 A CN101814159 A CN 101814159A
- Authority
- CN
- China
- Prior art keywords
- aann
- model
- gmm
- training
- network
- 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 65
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 24
- 239000000203 mixture Substances 0.000 title claims abstract description 17
- 238000012795 verification Methods 0.000 title claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 52
- 239000013598 vector Substances 0.000 claims description 53
- 230000008569 process Effects 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 10
- 230000008901 benefit Effects 0.000 abstract description 7
- 238000007476 Maximum Likelihood Methods 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 abstract description 2
- 238000013459 approach Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 241001014642 Rasta Species 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
Description
Claims (3)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009100244325A CN101814159B (zh) | 2009-02-24 | 2009-02-24 | 基于自联想神经网络和高斯混合背景模型相结合的说话人确认方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009100244325A CN101814159B (zh) | 2009-02-24 | 2009-02-24 | 基于自联想神经网络和高斯混合背景模型相结合的说话人确认方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101814159A true CN101814159A (zh) | 2010-08-25 |
CN101814159B CN101814159B (zh) | 2013-07-24 |
Family
ID=42621408
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2009100244325A Expired - Fee Related CN101814159B (zh) | 2009-02-24 | 2009-02-24 | 基于自联想神经网络和高斯混合背景模型相结合的说话人确认方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101814159B (zh) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102693724A (zh) * | 2011-03-22 | 2012-09-26 | 张燕 | 一种基于神经网络的高斯混合模型的噪声分类方法 |
CN102737633A (zh) * | 2012-06-21 | 2012-10-17 | 北京华信恒达软件技术有限公司 | 一种基于张量子空间分析的说话人识别方法及其装置 |
CN103221996A (zh) * | 2010-12-10 | 2013-07-24 | 松下电器产业株式会社 | 用于验证说话人的口令建模的设备和方法、以及说话人验证系统 |
WO2017076211A1 (zh) * | 2015-11-05 | 2017-05-11 | 阿里巴巴集团控股有限公司 | 基于语音的角色分离方法及装置 |
CN109326278A (zh) * | 2017-07-31 | 2019-02-12 | 科大讯飞股份有限公司 | 一种声学模型构建方法及装置、电子设备 |
CN110085255A (zh) * | 2019-03-27 | 2019-08-02 | 河海大学常州校区 | 语音转换基于深度内核学习高斯过程回归建模方法 |
CN112532547A (zh) * | 2020-11-21 | 2021-03-19 | 北京邮电大学 | 一种智能反射面通信系统中信道估计和信道鉴别方法 |
CN112820318A (zh) * | 2020-12-31 | 2021-05-18 | 西安合谱声学科技有限公司 | 一种基于gmm-ubm的冲击声模型建立、冲击声检测方法及系统 |
WO2021238274A1 (zh) * | 2020-05-28 | 2021-12-02 | 浪潮电子信息产业股份有限公司 | 一种分布式深度学习的梯度信息更新方法及相关装置 |
CN113822357A (zh) * | 2021-09-18 | 2021-12-21 | 广东工业大学 | 一种分类模型的训练方法、分类方法及相关装置 |
CN114708117A (zh) * | 2022-03-21 | 2022-07-05 | 广东电网有限责任公司 | 融合先验知识的用电安全检查评级方法、装置及设备 |
-
2009
- 2009-02-24 CN CN2009100244325A patent/CN101814159B/zh not_active Expired - Fee Related
Non-Patent Citations (2)
Title |
---|
秋政权,江太辉: "GMM/ANN混合说话人辨认模型", 《计算机工程与应用》 * |
黄伟 等: "基于分类特征空间高斯混合模型和神经网络融合的说话人识别", 《电子与信息学报》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103221996A (zh) * | 2010-12-10 | 2013-07-24 | 松下电器产业株式会社 | 用于验证说话人的口令建模的设备和方法、以及说话人验证系统 |
CN103221996B (zh) * | 2010-12-10 | 2015-09-30 | 松下电器(美国)知识产权公司 | 用于验证说话人的口令建模的设备和方法、以及说话人验证系统 |
US9257121B2 (en) | 2010-12-10 | 2016-02-09 | Panasonic Intellectual Property Corporation Of America | Device and method for pass-phrase modeling for speaker verification, and verification system |
CN102693724A (zh) * | 2011-03-22 | 2012-09-26 | 张燕 | 一种基于神经网络的高斯混合模型的噪声分类方法 |
CN102737633A (zh) * | 2012-06-21 | 2012-10-17 | 北京华信恒达软件技术有限公司 | 一种基于张量子空间分析的说话人识别方法及其装置 |
CN102737633B (zh) * | 2012-06-21 | 2013-12-25 | 北京华信恒达软件技术有限公司 | 一种基于张量子空间分析的说话人识别方法及其装置 |
WO2017076211A1 (zh) * | 2015-11-05 | 2017-05-11 | 阿里巴巴集团控股有限公司 | 基于语音的角色分离方法及装置 |
CN109326278B (zh) * | 2017-07-31 | 2022-06-07 | 科大讯飞股份有限公司 | 一种声学模型构建方法及装置、电子设备 |
CN109326278A (zh) * | 2017-07-31 | 2019-02-12 | 科大讯飞股份有限公司 | 一种声学模型构建方法及装置、电子设备 |
CN110085255A (zh) * | 2019-03-27 | 2019-08-02 | 河海大学常州校区 | 语音转换基于深度内核学习高斯过程回归建模方法 |
CN110085255B (zh) * | 2019-03-27 | 2021-05-28 | 河海大学常州校区 | 语音转换基于深度内核学习高斯过程回归建模方法 |
WO2021238274A1 (zh) * | 2020-05-28 | 2021-12-02 | 浪潮电子信息产业股份有限公司 | 一种分布式深度学习的梯度信息更新方法及相关装置 |
CN112532547B (zh) * | 2020-11-21 | 2022-03-01 | 北京邮电大学 | 一种智能反射面通信系统中信道估计和信道鉴别方法 |
CN112532547A (zh) * | 2020-11-21 | 2021-03-19 | 北京邮电大学 | 一种智能反射面通信系统中信道估计和信道鉴别方法 |
CN112820318A (zh) * | 2020-12-31 | 2021-05-18 | 西安合谱声学科技有限公司 | 一种基于gmm-ubm的冲击声模型建立、冲击声检测方法及系统 |
CN113822357A (zh) * | 2021-09-18 | 2021-12-21 | 广东工业大学 | 一种分类模型的训练方法、分类方法及相关装置 |
CN113822357B (zh) * | 2021-09-18 | 2024-01-05 | 广东工业大学 | 一种分类模型的训练方法、分类方法及相关装置 |
CN114708117A (zh) * | 2022-03-21 | 2022-07-05 | 广东电网有限责任公司 | 融合先验知识的用电安全检查评级方法、装置及设备 |
Also Published As
Publication number | Publication date |
---|---|
CN101814159B (zh) | 2013-07-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101814159B (zh) | 基于自联想神经网络和高斯混合背景模型相结合的说话人确认方法 | |
Sarangi et al. | Optimization of data-driven filterbank for automatic speaker verification | |
CN102693724A (zh) | 一种基于神经网络的高斯混合模型的噪声分类方法 | |
CN102034472A (zh) | 一种基于嵌入时延神经网络的高斯混合模型的说话人识别方法 | |
JPH11507443A (ja) | 話者確認システム | |
TWI475558B (zh) | 詞語驗證的方法及裝置 | |
Tüske et al. | Deep hierarchical bottleneck MRASTA features for LVCSR | |
Mallidi et al. | Uncertainty estimation of DNN classifiers | |
Revathi et al. | Speaker independent continuous speech and isolated digit recognition using VQ and HMM | |
CN104240706A (zh) | 一种基于GMM Token配比相似度校正得分的说话人识别方法 | |
Mallidi et al. | Autoencoder based multi-stream combination for noise robust speech recognition. | |
Adiban et al. | Sut system description for anti-spoofing 2017 challenge | |
Fasounaki et al. | CNN-based Text-independent automatic speaker identification using short utterances | |
Maghsoodi et al. | Speaker recognition with random digit strings using uncertainty normalized HMM-based i-vectors | |
Rouvier et al. | Review of different robust x-vector extractors for speaker verification | |
Tsao et al. | An acoustic segment model approach to incorporating temporal information into speaker modeling for text-independent speaker recognition | |
BenZeghiba et al. | User-customized password speaker verification using multiple reference and background models | |
Li et al. | A Convolutional Neural Network with Non-Local Module for Speech Enhancement. | |
Zhang et al. | Non-parallel sequence-to-sequence voice conversion for arbitrary speakers | |
Dey et al. | Content normalization for text-dependent speaker verification | |
Do et al. | A new speaker identification algorithm for gaming scenarios | |
Yee et al. | Malay language text-independent speaker verification using NN-MLP classifier with MFCC | |
You et al. | Ustcspeech system for voices from a distance challenge 2019 | |
Nathwani et al. | Consistent DNN uncertainty training and decoding for robust ASR | |
Makishima et al. | Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
ASS | Succession or assignment of patent right |
Owner name: NANJING INSTITUTE OF TECHNOLOGY Free format text: FORMER OWNER: YU HUA Effective date: 20130613 |
|
C41 | Transfer of patent application or patent right or utility model | ||
C53 | Correction of patent of invention or patent application | ||
CB03 | Change of inventor or designer information |
Inventor after: Bao Yongqiang Inventor after: Yu Hua Inventor after: Chen Cunbao Inventor after: Zhao Li Inventor after: Wei Xin Inventor after: Xi Ji Inventor after: Wang Qingyun Inventor after: Liang Ruiyu Inventor after: Wang Hao Inventor before: Yu Hua Inventor before: Dai Hongxia Inventor before: Chen Cunbao Inventor before: Zhao Li Inventor before: Wei Xin Inventor before: Xi Ji Inventor before: Wang Qingyun Inventor before: Liang Ruiyu |
|
COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 210096 NANJING, JIANGSU PROVINCE TO: 211167 NANJING, JIANGSU PROVINCE Free format text: CORRECT: INVENTOR; FROM: YU HUA DAI HONGXIA CHEN CUNBAO ZHAO LI WEI XIN XI JI WANG QINGYUN LIANG RUIYU TO: BAO YONGQIANG YU HUA CHEN CUNBAO ZHAO LI WEI XIN XI JI WANG QINGYUN LIANG RUIYU WANG HAO |
|
TA01 | Transfer of patent application right |
Effective date of registration: 20130613 Address after: Park Avenue in Jiangning District of Nanjing City, 211167 Hong Jing Jiangsu province Nanjing Institute of Technology No. 1 Applicant after: NANJING INSTITUTE OF TECHNOLOGY Address before: Nanjing Vocational College of Information Technology Applicant before: Yu Hua |
|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130724 Termination date: 20140224 |