Edinburgh Research Explorer

Noise Compensation for Subspace Gaussian Mixture Models.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationINTERSPEECH 2012 13th Annual Conference of the International Speech Communication Association
PublisherISCA
Pages306-309
Number of pages4
Publication statusPublished - 2012

Abstract

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.

Download statistics

No data available

ID: 12305229