Exploiting prosodic information for Speaker Recognition
Lists
Only you see this
Abstract
In this paper, we study speaker characterization using prosodic supervectors with negative within-class covariance normalization (NWCCN) projection and speaker modeling with support vector regression (SVR). We also propose a segmental weight fusion (SWF) technique that combines acoustic and prosodic subsystems effectively, despite the big performance gap between the subsystems. We validate the effectiveness of our proposed techniques on the NIST 2006 Speaker Recognition Evaluation (SRE) in comparison with other prominent solutions. The experiments have reported competitive results of 17.72% Equal Error Rate for the prosodic subsystem alone and 4.50% for the fusion system on NIST 2006 SRE core test condition.
BibTeX
@inproceedings{long2009exploiting,
author = {Yanhua Long and Bin Ma and Haizhou Li and Wu Guo and Chng Eng Siong and Li-Rong Dai},
title = {{Exploiting prosodic information for Speaker Recognition}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2009},
doi = {10.1109/icassp.2009.4960561},
}Loading related content...