Papers

Normalized minimum-redundancy and maximum-relevancy based feature selection for speaker verification systems

International Conference
2006~2010
작성자
한혜원
작성일
2009-04-19 23:40
조회
1585
Authors : Chi-Sang Jung, Moo-Young Kim, Hong-Goo Kang

Year : 2009

Publisher / Conference : ICASSP

Page : 4549-4552

In this paper, an information theoretical approach to select features for speaker recognition systems is proposed. Conventional approaches having a fixed interval of analysis frames are not appropriate to represent dynamically varying characteristics of speech signals. To maximize the speaker-related information varied by the characteristics of speech signals, we propose an information theory based feature selection method where features are selected to have minimum-redundancy with in selected features but maximumrelevancy to training speaker models. Experimental results verify that the proposed method reduces the error rates of speaker verification systems by 27.37 % in NIST 2002 database.
전체 363
47 International Conference Se-Woon Jeon, Young-Cheol Park, Seok-Pil Lee, Dae Hee Youn "Robust Representation of Spatial Sound in Stereo-to-Multichannel Upmix" in 128th Convention of Audio Engineering Society, pp.7976, 2010
46 International Conference Se-Woon Jeon, Dongil Hyun, Jeongil Seo, Young-Cheol Park, Dae Hee Youn "Enhancement of principal to ambient energy ratio for PCA-based parametric audio coding" in ICASSP, 2010
45 International Conference Ho Seon Shin, Min-Seok Choi, Taesu Kim, Hong-Goo Kang "Binaural loudness based speech reinforcement with a closed-form solution" in ICASSP, 2010
44 International Conference SoonHo Beak, Myung-Suk Song, Seok-Pil Lee, Hong-Goo Kang "Speaker Array System Based on Equalization Method with a Quiet Zone" in 127th Convention of Audio Engineering Society, pp.7951, 2009
43 International Conference Dongil Hyun, Jeongil Seo, Youngcheol Park, Daehee Youn "Robust Interchannel Correlation (ICC) Estimation Using Constant Interchannel Time Difference (ICTD) Compensation" in 127th Convention of Audio Engineering Society, pp.7934, 2009
42 International Conference Jae-Mo Yang, Chang-Heon Lee, Hong-Goo Kang "A robust time difference of arrival estimator in reverberant environments" in EUSIPCO, 2009
41 International Conference Ho Seon Shin, Hong-Goo Kang, Min-Seok Choi, Taesu Kim "SPEECH REINFORCEMENT BASED ON BINAURAL LOUDNESS MODEL" in The Fourth Beijing-Hong Kong International Doctoral Forum, 2009
40 International Conference Chi-Sang Jung, Moo-Young Kim, Hong-Goo Kang "Normalized minimum-redundancy and maximum-relevancy based feature selection for speaker verification systems" in ICASSP, pp.4549-4552, 2009
39 International Conference Dongil-Hyun,Tacksung Choi, Daehee Youn, Seokpil Lee, Youngcheol Park "The Use of Delay Control for Stereophonic Audio Rendering Based on VBAP" in 125th Convention of Audio Engineering Society, pp.7603, 2008
38 International Conference Gun-Woo Lee, Jae-sung Lee, Young-Cheol Park, Dae Hee Youn "Quality Improvement of Very Low Bit Rate HE-AAC Using Linear Prediction Module" in 125th Convention of Audio Engineering Society, pp.7624, 2008