12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Discriminatively Trained i-vector Extractor for Speaker Verification

Ondřej Glembek (1), Lukáš Burget (1), Niko Brümmer (2), Oldřich Plchot (1), Pavel Matějka (1)

(1) Brno University of Technology, Czech Republic
(2) Agnitio, South Africa

We propose a strategy for discriminative training of the i-vector extractor in speaker recognition. The original i-vector extractor training was based on the maximum-likelihood generative modeling, where the EM algorithm was used. In our approach, the i-vector extractor parameters are numerically optimized to minimize the discriminative cross-entropy error function. Two versions of the i-vector extraction are studied - the original approach as defined for Joint Factor Analysis, and the simplified version, where orthogonalization of the i-vector extractor matrix is performed.

Full Paper

Bibliographic reference.  Glembek, Ondřej / Burget, Lukáš / Brümmer, Niko / Plchot, Oldřich / Matějka, Pavel (2011): "Discriminatively trained i-vector extractor for speaker verification", In INTERSPEECH-2011, 137-140.