On the use of voting methods for speaker identification based on various resolution filterbanks

Bong Jin Lee; Sung Wan Yoon; Hong Goo Kang; Dae Hee Youn

On the use of voting methods for speaker identification based on various resolution filterbanks

Bong Jin Lee, Sung Wan Yoon, Hong Goo Kang, Dae Hee Youn

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

This paper proposes a novel speaker identification system based on score fusion of various resolution filterbanks. The proposed system uses multiple features which are extracted from filterbanks having various spectral resolutions. Each speaker model is constructed by independent feature set, but the system makes final decision by combining the outcome of each model. We introduce several well-known voting methods for decision. Simulation results using TIMIT database show that the proposed score fusion method significantly improves speaker identification performance compared to single model one. Especially, 59.28% of relative improvement is achieved by using a product rule.

Original language	English
Title of host publication	2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
Pages	I917-I920
Publication status	Published - 2006
Event	2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006 - Toulouse, France Duration: 2006 May 14 → 2006 May 19

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	1
ISSN (Print)	1520-6149

Other

Other	2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006
Country	France
City	Toulouse
Period	06/5/14 → 06/5/19

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'On the use of voting methods for speaker identification based on various resolution filterbanks'. Together they form a unique fingerprint.

Cite this

Lee, B. J., Yoon, S. W., Kang, H. G., & Youn, D. H. (2006). On the use of voting methods for speaker identification based on various resolution filterbanks. In 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings (pp. I917-I920). [1660171] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 1).

Lee, Bong Jin ; Yoon, Sung Wan ; Kang, Hong Goo ; Youn, Dae Hee. / On the use of voting methods for speaker identification based on various resolution filterbanks. 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings. 2006. pp. I917-I920 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{e986e1b1fdd0430e97577b64fbe7bae7,

title = "On the use of voting methods for speaker identification based on various resolution filterbanks",

abstract = "This paper proposes a novel speaker identification system based on score fusion of various resolution filterbanks. The proposed system uses multiple features which are extracted from filterbanks having various spectral resolutions. Each speaker model is constructed by independent feature set, but the system makes final decision by combining the outcome of each model. We introduce several well-known voting methods for decision. Simulation results using TIMIT database show that the proposed score fusion method significantly improves speaker identification performance compared to single model one. Especially, 59.28% of relative improvement is achieved by using a product rule.",

author = "Lee, {Bong Jin} and Yoon, {Sung Wan} and Kang, {Hong Goo} and Youn, {Dae Hee}",

note = "Copyright: Copyright 2008 Elsevier B.V., All rights reserved.; 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006 ; Conference date: 14-05-2006 Through 19-05-2006",

year = "2006",

language = "English",

isbn = "142440469X",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "I917--I920",

booktitle = "2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings",

}

Lee, BJ, Yoon, SW, Kang, HG & Youn, DH 2006, On the use of voting methods for speaker identification based on various resolution filterbanks. in 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings., 1660171, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 1, pp. I917-I920, 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006, Toulouse, France, 06/5/14.

On the use of voting methods for speaker identification based on various resolution filterbanks. / Lee, Bong Jin; Yoon, Sung Wan; Kang, Hong Goo; Youn, Dae Hee.

2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings. 2006. p. I917-I920 1660171 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - On the use of voting methods for speaker identification based on various resolution filterbanks

AU - Lee, Bong Jin

AU - Yoon, Sung Wan

AU - Kang, Hong Goo

AU - Youn, Dae Hee

PY - 2006

Y1 - 2006

N2 - This paper proposes a novel speaker identification system based on score fusion of various resolution filterbanks. The proposed system uses multiple features which are extracted from filterbanks having various spectral resolutions. Each speaker model is constructed by independent feature set, but the system makes final decision by combining the outcome of each model. We introduce several well-known voting methods for decision. Simulation results using TIMIT database show that the proposed score fusion method significantly improves speaker identification performance compared to single model one. Especially, 59.28% of relative improvement is achieved by using a product rule.

AB - This paper proposes a novel speaker identification system based on score fusion of various resolution filterbanks. The proposed system uses multiple features which are extracted from filterbanks having various spectral resolutions. Each speaker model is constructed by independent feature set, but the system makes final decision by combining the outcome of each model. We introduce several well-known voting methods for decision. Simulation results using TIMIT database show that the proposed score fusion method significantly improves speaker identification performance compared to single model one. Especially, 59.28% of relative improvement is achieved by using a product rule.

UR - http://www.scopus.com/inward/record.url?scp=33947654384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947654384&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33947654384

SN - 142440469X

SN - 9781424404698

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - I917-I920

BT - 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings

T2 - 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006

Y2 - 14 May 2006 through 19 May 2006

ER -