By Topic

Noise robust speaker verification using parallel model combination and local features

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Z. Tufekci ; Izmir Yuksek Teknoloji Enstitusu, Turkey

Interfering noise severely degrades the performance of a speaker verification system. The parallel model combination (PMC) technique is one of the most efficient techniques for dealing with such noise. Another method is to use features local in the frequency domain. Recently, we proposed Mel-frequency discrete wavelet coefficients (MFDWCs) (Gowdy, J. and Tufekci, Z., Proc. ICASSP, 2000) as speech features local in the frequency domain. We now discuss using PMC along with MFDWC features to take advantage of both noise compensation and local features (MFDWCs) to decrease the effect of noise on verification performance. We evaluate the performance of MFDWCs for various noise types and noise levels. We also compare the performance of these versus MFCCs and both using PMC for dealing with additive noise. The experimental results show significant performance improvements for MFDWCs versus MFCCs after compensating the HMMs using the PMC technique. For example, the MFDWCs gave 6.29 points performance improvement on average over MFCCs for 12 dB. This corresponds to 38.33% error reduction.

Published in:

Signal Processing and Communications Applications Conference, 2004. Proceedings of the IEEE 12th

Date of Conference:

28-30 April 2004