A Generalized Feature Transformation Approach for Channel Robust Speaker Verification

Donglai Zhu, Bin Ma, Haizhou Li, Qiang Huo

Abstract

In this paper we propose a generalized feature transformation approach to compensating for channel variation in speaker verification (SV) applications. Channel-dependent (CD) piecewise linear transformations are used for feature compensation. CD transformation parameters are estimated together with a channel-independent (CI) root Gaussian mixture model (GMM) from training data with a variety of channel conditions by using a maximum likelihood criterion. Experiments are conducted on the 2005 NIST Speaker Recognition Evaluation (SRE) corpus for several text-independent GMM-based SV systems. Experimental results show that the proposed approach achieves relative equal error rate (EER) reductions of 8.19% and 26.24% in comparison with a traditional feature mapping approach and a baseline system, respectively.
BibTeX
@inproceedings{zhu2007generalized,
  author = {Donglai Zhu and Bin Ma and Haizhou Li and Qiang Huo},
  title = {{A Generalized Feature Transformation Approach for Channel Robust Speaker Verification}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2007},
  doi = {10.1109/icassp.2007.367163},
}

Loading related content...

Figure