Previous work has demonstrated the promise of frame-level quality measure methods to robust speaker recognition. This paper explores the issues involved in applying soft estimates to quality measures as weighting factors in score computation. A quality measure algorithm using Gaussian mixture density and Jensen divergence measure is presented for traditional GMM-UBM scoring mechanism. Derivation and validation of the quality measurement are reported in this paper. We investigate the usefulness of different feature processing, different GMM-based quality models and incorporation of divergence measure for quality estimation. Comparison experiments performed on the NIST1999 SRE corpus show the effectiveness of the proposed method.
Cite as: Zheng, R., Zhang, S., Xu, B. (2006) A quality measure method using Gaussian mixture models and divergence measure for speaker identification. Proc. Interspeech 2006, paper 1328-Wed3CaP.5, doi: 10.21437/Interspeech.2006-189
@inproceedings{zheng06_interspeech,
author={Rong Zheng and Shuwu Zhang and Bo Xu},
title={{A quality measure method using Gaussian mixture models and divergence measure for speaker identification}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1328-Wed3CaP.5},
doi={10.21437/Interspeech.2006-189}
}