Edinburgh Research Explorer

Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models

Research output: Contribution to journalArticle

Original languageEnglish
Pages (from-to)1791-1804
Number of pages14
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume21
Issue number9
Early online date22 Feb 2013
DOIs
Publication statusPublished - Sep 2013

Abstract

Joint uncertainty decoding (JUD) is a model-based noise compensation technique for conventional Gaussian Mixture Model (GMM) based speech recognition systems. Unlike vector Taylor series (VTS) compensation which operates on the individual Gaussian components in an acoustic model, JUD clusters the Gaussian components into a smaller number of classes, sharing the compensation parameters for the set of Gaussians in a given class. This significantly reduces the computational cost. In this paper, we investigate noise compensation for subspace Gaussian mixture model (SGMM) based speech recognition systems using JUD. The total number of Gaussian components in an SGMM is typically very large. Therefore direct compensation of the individual Gaussian components, as performed by VTS, is computationally expensive. In this paper we show that JUD-based noise compensation can be successfully applied to SGMMs in a computationally efficient way. We evaluate the JUD/SGMM technique on the standard Aurora 4 corpus. Our experimental results indicate that the JUD/SGMM system results in lower word error rates compared with a conventional GMM system with either VTS-based or JUD-based noise compensation.

    Research areas

  • joint uncertainty decoding, vector Taylor series, Aurora 4, subspace Gaussian mixture model, noise robust ASR

Download statistics

No data available

ID: 8220867