Cost-Sensitive Learning for Emotion Robust Speaker Recognition

In the field of information security, voice is one of the most important parts in biometrics. Especially, with the development of voice communication through the Internet or telephone system, huge voice data resources are accessed. In speaker recognition, voiceprint can be applied as the unique pass...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongdong Li, Yingchun Yang, Weihui Dai
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1155/2014/628516
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849468286286168064
author Dongdong Li
Yingchun Yang
Weihui Dai
author_facet Dongdong Li
Yingchun Yang
Weihui Dai
author_sort Dongdong Li
collection DOAJ
description In the field of information security, voice is one of the most important parts in biometrics. Especially, with the development of voice communication through the Internet or telephone system, huge voice data resources are accessed. In speaker recognition, voiceprint can be applied as the unique password for the user to prove his/her identity. However, speech with various emotions can cause an unacceptably high error rate and aggravate the performance of speaker recognition system. This paper deals with this problem by introducing a cost-sensitive learning technology to reweight the probability of test affective utterances in the pitch envelop level, which can enhance the robustness in emotion-dependent speaker recognition effectively. Based on that technology, a new architecture of recognition system as well as its components is proposed in this paper. The experiment conducted on the Mandarin Affective Speech Corpus shows that an improvement of 8% identification rate over the traditional speaker recognition is achieved.
format Article
id doaj-art-f7438edb6cff4e00bfb6a9dbefa7243e
institution Kabale University
issn 2356-6140
1537-744X
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series The Scientific World Journal
spelling doaj-art-f7438edb6cff4e00bfb6a9dbefa7243e2025-08-20T03:25:53ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/628516628516Cost-Sensitive Learning for Emotion Robust Speaker RecognitionDongdong Li0Yingchun Yang1Weihui Dai2School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, ChinaDepartment of Computer Science and Technology, Zhejiang University, No. 38, Yuquan Road, Zhejiang 310027, ChinaSchool of Management, Fudan University, No. 220, Handan Road, Shanghai 200433, ChinaIn the field of information security, voice is one of the most important parts in biometrics. Especially, with the development of voice communication through the Internet or telephone system, huge voice data resources are accessed. In speaker recognition, voiceprint can be applied as the unique password for the user to prove his/her identity. However, speech with various emotions can cause an unacceptably high error rate and aggravate the performance of speaker recognition system. This paper deals with this problem by introducing a cost-sensitive learning technology to reweight the probability of test affective utterances in the pitch envelop level, which can enhance the robustness in emotion-dependent speaker recognition effectively. Based on that technology, a new architecture of recognition system as well as its components is proposed in this paper. The experiment conducted on the Mandarin Affective Speech Corpus shows that an improvement of 8% identification rate over the traditional speaker recognition is achieved.http://dx.doi.org/10.1155/2014/628516
spellingShingle Dongdong Li
Yingchun Yang
Weihui Dai
Cost-Sensitive Learning for Emotion Robust Speaker Recognition
The Scientific World Journal
title Cost-Sensitive Learning for Emotion Robust Speaker Recognition
title_full Cost-Sensitive Learning for Emotion Robust Speaker Recognition
title_fullStr Cost-Sensitive Learning for Emotion Robust Speaker Recognition
title_full_unstemmed Cost-Sensitive Learning for Emotion Robust Speaker Recognition
title_short Cost-Sensitive Learning for Emotion Robust Speaker Recognition
title_sort cost sensitive learning for emotion robust speaker recognition
url http://dx.doi.org/10.1155/2014/628516
work_keys_str_mv AT dongdongli costsensitivelearningforemotionrobustspeakerrecognition
AT yingchunyang costsensitivelearningforemotionrobustspeakerrecognition
AT weihuidai costsensitivelearningforemotionrobustspeakerrecognition