A Multiscale Chaotic Feature Extraction Method for Speaker Recognition

In speaker recognition systems, feature extraction is a challenging task under environment noise conditions. To improve the robustness of the feature, we proposed a multiscale chaotic feature for speaker recognition. We use a multiresolution analysis technique to capture more finer information on di...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiang Lin, Yi Yumei, Zhang Maosheng, Chen Defeng, Wang Chao, Wang Tonghan
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/8810901
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849404592589111296
author Jiang Lin
Yi Yumei
Zhang Maosheng
Chen Defeng
Wang Chao
Wang Tonghan
author_facet Jiang Lin
Yi Yumei
Zhang Maosheng
Chen Defeng
Wang Chao
Wang Tonghan
author_sort Jiang Lin
collection DOAJ
description In speaker recognition systems, feature extraction is a challenging task under environment noise conditions. To improve the robustness of the feature, we proposed a multiscale chaotic feature for speaker recognition. We use a multiresolution analysis technique to capture more finer information on different speakers in the frequency domain. Then, we extracted the speech chaotic characteristics based on the nonlinear dynamic model, which helps to improve the discrimination of features. Finally, we use a GMM-UBM model to develop a speaker recognition system. Our experimental results verified its good performance. Under clean speech and noise speech conditions, the ERR value of our method is reduced by 13.94% and 26.5% compared with the state-of-the-art method, respectively.
format Article
id doaj-art-9b340deb0a7f4a2f851f7cb221b37b10
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-9b340deb0a7f4a2f851f7cb221b37b102025-08-20T03:36:57ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88109018810901A Multiscale Chaotic Feature Extraction Method for Speaker RecognitionJiang Lin0Yi Yumei1Zhang Maosheng2Chen Defeng3Wang Chao4Wang Tonghan5College of Computer and Information Engineering, Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, ChinaCollege of Computer and Information Engineering, Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, ChinaSchool of Mathematics and Statistics, Yulin Normal University, Yulin 537000, ChinaCollege of Computer and Information Engineering, Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, ChinaNational Engineering Research Center for Multimedia Software, Wuhan University, Wuhan 430072, ChinaSchool of Software, East China University of Technology, Nanchang 330013, ChinaIn speaker recognition systems, feature extraction is a challenging task under environment noise conditions. To improve the robustness of the feature, we proposed a multiscale chaotic feature for speaker recognition. We use a multiresolution analysis technique to capture more finer information on different speakers in the frequency domain. Then, we extracted the speech chaotic characteristics based on the nonlinear dynamic model, which helps to improve the discrimination of features. Finally, we use a GMM-UBM model to develop a speaker recognition system. Our experimental results verified its good performance. Under clean speech and noise speech conditions, the ERR value of our method is reduced by 13.94% and 26.5% compared with the state-of-the-art method, respectively.http://dx.doi.org/10.1155/2020/8810901
spellingShingle Jiang Lin
Yi Yumei
Zhang Maosheng
Chen Defeng
Wang Chao
Wang Tonghan
A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
Complexity
title A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
title_full A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
title_fullStr A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
title_full_unstemmed A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
title_short A Multiscale Chaotic Feature Extraction Method for Speaker Recognition
title_sort multiscale chaotic feature extraction method for speaker recognition
url http://dx.doi.org/10.1155/2020/8810901
work_keys_str_mv AT jianglin amultiscalechaoticfeatureextractionmethodforspeakerrecognition
AT yiyumei amultiscalechaoticfeatureextractionmethodforspeakerrecognition
AT zhangmaosheng amultiscalechaoticfeatureextractionmethodforspeakerrecognition
AT chendefeng amultiscalechaoticfeatureextractionmethodforspeakerrecognition
AT wangchao amultiscalechaoticfeatureextractionmethodforspeakerrecognition
AT wangtonghan amultiscalechaoticfeatureextractionmethodforspeakerrecognition
AT jianglin multiscalechaoticfeatureextractionmethodforspeakerrecognition
AT yiyumei multiscalechaoticfeatureextractionmethodforspeakerrecognition
AT zhangmaosheng multiscalechaoticfeatureextractionmethodforspeakerrecognition
AT chendefeng multiscalechaoticfeatureextractionmethodforspeakerrecognition
AT wangchao multiscalechaoticfeatureextractionmethodforspeakerrecognition
AT wangtonghan multiscalechaoticfeatureextractionmethodforspeakerrecognition