Dealing with acoustic mismatch for training multilingual subspace Gaussian mixture models for speech recognition
Authors:
- 1 March 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4893-4896
Abstract
The subspace Gaussian mixture model (SGMM) has been recently proposed as an acoustic modeling technique suitable for configuring multilingual speech recognition systems. It is attractive for this purpose since its parametrization allows its “shared” model parameters to be trained with data from multiple languages [1]. In this work, we report on the results of an experimental study carried out with the goal of improving native Spanish language speech recognition performance using an existing telephone speech corpus of English spoken by speakers of Spanish origin. Compensation for sources of acoustic variability between Spanish and English language data sets was found to be important in obtaining good multilingual ASR performance. We conclude with a discussion about the notion of acoustic similarity between the state dependent parameters of the SGMM, and its possible use in effectively modelling pronunciation variation.Keywords
This publication has 8 references indexed in Scilit:
- Acoustic data sharing for Afghan and Persian languages2011
- Cross-language bootstrapping based on completely unsupervised training using multilingual A-stabil2011
- An investigation of subspace modeling for phonetic and speaker variability in automatic speech recognition2011
- The subspace Gaussian mixture model—A structured model for speech recognitionComputer Speech & Language, 2011
- Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models2010
- A study on multilingual acoustic modeling for large vocabulary ASR2009
- Language-dependent state clustering for multilingual acoustic modellingSpeech Communication, 2007
- Language-independent and language-adaptive acoustic modeling for speech recognitionSpeech Communication, 2001