论文信息 - Speaker verification using text-constrained Gaussian Mixture Models

Speaker verification using text-constrained Gaussian Mixture Models

In this paper we present an approach to close the gap between text-dependent and text-independent speaker verification performance. Text-constrained GMM-UBM systems are created using word segmentations produced by a LVCSR system on conversational speech allowing the system to focus on speaker differences over a constrained set of acoustic units. Results on the 2001 NIST extended data task show this approach can be used to produce an equal error rate of < 1 %.

[1] Joseph P. Campbell,et al. Phonetic, idiolectal and acoustic speaker recognition , 2001, Odyssey.

[2] Douglas A. Reynolds,et al. Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[3] J.P. Eatock,et al. A quantitative assessment of the relative speaker discriminating properties of phonemes , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[4] Some Experiments on Idiolectal Differences among Speakers 1 Motivation , 2000 .

[5] Douglas A. Reynolds,et al. The NIST speaker recognition evaluation - Overview, methodology, systems, results, perspective , 2000, Speech Commun..

[6] Larry Gillick,et al. Speaker Recognition on Single- and Multispeaker Data , 2000, Digit. Signal Process..