13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Noise Compensation for Subspace Gaussian Mixture Models

Liang Lu (1), K. K. Chin (2), Arnab Ghoshal (1), Steve Renals (1)

(1) Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK
(2) Toshiba Research Europe Ltd, Cambridge Research Laboratory, Cambridge, UK

Joint uncertainty decoding (JUD) is an effective model-based noise compensation technique for conventional Gaussian mixture model (GMM) based speech recognition systems. In this paper, we apply JUD to subspace Gaussian mixture model (SGMM) based acoustic models. The total number of Gaussians in the SGMM acoustic model is usually much larger than for conventional GMMs, which limits the application of approaches which explicitly compensate each Gaussian, such as vector Taylor series (VTS). However, by clustering the Gaussian components into a number of regression classes, JUD-based noise compensation can be successfully applied to SGMM systems. We evaluate the JUD/SGMM technique using the Aurora 4 corpus, and the experimental results indicated that it is more accurate than conventional GMM-based systems using either VTS or JUD noise compensation.

Full Paper

Bibliographic reference.  Lu, Liang / Chin, K. K. / Ghoshal, Arnab / Renals, Steve (2012): "Noise compensation for subspace Gaussian mixture models", In INTERSPEECH-2012, 306-309.