8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

A New Approach to Channel Robust Speaker Verification via Constrained Stochastic Feature Transformation

Man-Wai Mak (1), Kwok-kwong Yiu (1), Ming-Cheung Cheung(1), Sun-Yuan Kung (2)

The Hong Kong Polytechnic University, Hong Kong
(2) Princeton University, USA

This paper proposes a constrained stochastic feature transformation algorithm for robust speaker verification. The algorithm computes the feature transformation parameters based on the statistical difference between a test utterance and a composite GMM formed by combining the speaker and background model. The transformation is then used to transform the test utterance to fit the clean speaker model and background model before verification. By implicitly constraining the transformation, the transformed features can fit both models simultaneously. Experimental results based on the 2001 NIST evaluation set show that the proposed algorithms achieves significant improvement in both equal error rate and minimum detection cost when compared to cepstral mean subtraction and Z-norm. The performance of the proposed transformation approach is also slightly better than the short-time Gaussianization method proposed in [1].

Full Paper

Bibliographic reference.  Mak, Man-Wai / Yiu, Kwok-kwong / Cheun, Ming-Cheung / Kung, Sun-Yuan (2004): "A new approach to channel robust speaker verification via constrained stochastic feature transformation", In INTERSPEECH-2004, 1753-1756.