INTERSPEECH 2009
10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics

Niko Brümmer (1), Albert Strasheim (1), Valiantsina Hubeika (2), Pavel Matějka (2), Lukáš Burget (2), Ondřej Glembek (2)

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

We propose a novel design for acoustic feature-based automatic spoken language recognizers. Our design is inspired by recent advances in text-independent speaker recognition, where intraclass variability is modeled by factor analysis in Gaussian mixture model (GMM) space. We use approximations to GMM-likelihoods which allow variable-length data sequences to be represented as statistics of fixed size. Our experiments on NIST LRE’07 show that variability-compensation of these statistics can reduce error-rates by a factor of three. Finally, we show that further improvements are possible with discriminative logistic regression training.

Full Paper

Bibliographic reference.  Brümmer, Niko / Strasheim, Albert / Hubeika, Valiantsina / Matějka, Pavel / Burget, Lukáš / Glembek, Ondřej (2009): "Discriminative acoustic language recognition via channel-compensated GMM statistics", In INTERSPEECH-2009, 2187-2190.