LS Regularization of Group Delay Features for Speaker Recognition

被引：0

作者：

Kua, Jia Min Karen ^{[1
,2
]}

Epps, Julien ^{[1
,2
]}

Ambikairajah, Eliathamby ^{[1
,2
]}

Choi, Eric ^{[2
]}

机构：

[1] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia

[2] Natl ICT Australia NICTA, ATP Res Lab, Eveleigh 2015, Australia

来源：

INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | 2009年

关键词：

speaker recognition; group delay; least squares regularization;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Due to the increasing use of fusion in speaker recognition systems, features that are complementary to MFCCs offer opportunities to advance the state of the art. One promising feature is based on group delay, however this can suffer large variability due to its numerical formulation. In this paper, we investigate reducing this variability in group delay features with least squares regularization. Evaluations on the NIST 2001 and 2008 SRE databases show a relative improvement of at least 6% and 18% EER respectively when group delay-based system is fused with MFCC-based system.

引用

页码：2851 / +

页数：2

共 15 条

[1] Banno H, 1998, INT CONF ACOUST SPEE, P861, DOI 10.1109/ICASSP.1998.675401
[2] BROOKES D.M., 1994, PROC I ACOUSTICS, V16, P501
[3] Campbell WM, 2006, INT CONF ACOUST SPEE, P97
[4] Hegde RM, 2004, 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, P517
[5] HEGDE RM, 2003, INT C NAT LANG PROC
[6] Cluster-based visualisation with scatter matrices
Lisboa, N. G.
Ellis, I. O.
Green, A. R.
Ambrogi, F.
Dias, M. B.
[J]. PATTERN RECOGNITION LETTERS, 2008, 29 (13) : 1814 - 1823
[7] ENERGY SEPARATION IN SIGNAL MODULATIONS WITH APPLICATION TO SPEECH ANALYSIS
MARAGOS, P
KAISER, JF
QUATIERI, TF
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1993, 41 (10) : 3024 - 3051
[8] SPEECH PROCESSING USING GROUP DELAY FUNCTIONS
MURTHY, HA
YEGNANARAYANA, B
[J]. SIGNAL PROCESSING, 1991, 22 (03) : 259 - 267
[9] Murthy HA, 2003, 2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, P68
[10] Modeling of the glottal flow derivative waveform with application to speaker identification
Plumpe, MD
Quatieri, TF
Reynolds, DA
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1999, 7 (05): : 569 - 586

← 1 2 →