9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Robust Speaker Verification Using Short-Time Frequency with Long-Time Window and Fusion of Multi-Resolutions

Chien-Lin Huang (1), Bin Ma (2), Chung-Hsien Wu (1), Brian Mak (3), Haizhou Li (2)

(1) National Cheng Kung University, Taiwan;
(2) Institute for Infocomm Research, Singapore
(3) Hong Kong University of Science & Technology, China

This study presents a novel approach of feature analysis to speaker verification. There are two main contributions in this paper. First, the feature analysis of short-time frequency with long-time window (SFLW) is a compact feature for the efficiency of speaker verification. The purpose of SFLW is to take account of short-time frequency characteristics and long-time resolution at the same time. Secondly, the fusion of multi-resolutions is used for the effectiveness of robust speaker verification. The speaker verification system can be further improved using multi-resolution features. The experimental results indicate that the proposed approaches not only speed up the processing time but also improve the performance of speaker verification.

Full Paper

Bibliographic reference.  Huang, Chien-Lin / Ma, Bin / Wu, Chung-Hsien / Mak, Brian / Li, Haizhou (2008): "Robust speaker verification using short-time frequency with long-time window and fusion of multi-resolutions", In INTERSPEECH-2008, 1897-1900.