At present, most speaker identification systems use cepstral or linear prediction (IP) based features. The performance of these systems degrades significantly with the presence of noise in the training and/or the testing speech. To improve this performance, higher order statistics (HOS) or cumulant-based LF features are proposed. Using these features and singular value decomposition (SVD), it is shown that the performance of a speaker identification system can be improved considerably in the presence of additive white or colored Gaussian noise.
Cite as: Trent, L.J., Rader, C.M., Reynolds, D.A. (1994) Using higher order statistics to increase the noise robustness of a speaker identification system. Proc. ESCA Workshop on Automatic Speaker Recognition, Identification and Verification, 221-224
@inproceedings{trent94_asriv,
author={Larry J. Trent and Charles M. Rader and Douglas A. Reynolds},
title={{Using higher order statistics to increase the noise robustness of a speaker identification system}},
year=1994,
booktitle={Proc. ESCA Workshop on Automatic Speaker Recognition, Identification and Verification},
pages={221--224}
}