Abstract
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 models. 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].
Original language | English |
---|---|
Title of host publication | 8th International Conference on Spoken Language Processing, ICSLP 2004 |
Publisher | International Speech Communication Association |
Pages | 1753-1756 |
Number of pages | 4 |
Publication status | Published - 1 Jan 2004 |
Event | 8th International Conference on Spoken Language Processing, ICSLP 2004 - International Convention Center, Jeju, Jeju Island, Korea, Republic of Duration: 4 Oct 2004 → 8 Oct 2004 |
Conference
Conference | 8th International Conference on Spoken Language Processing, ICSLP 2004 |
---|---|
Country/Territory | Korea, Republic of |
City | Jeju, Jeju Island |
Period | 4/10/04 → 8/10/04 |
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language