An experimental study of acoustic adaptation algorithms
- 23 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 713-716
- https://doi.org/10.1109/icassp.1996.543220
Abstract
There has been much interest in the area of adaptation for improved speech recognition in the presence of mismatches between the training and testing conditions. We focus on transformation-based maximum-likelihood (ML) adaptation. Some of the important adaptation parameters include whether the adaptation is performed in the feature-space or model-space, and whether the adaptation is supervised or unsupervised. An additional parameter is the adaptation data. For example adaptation may be performed using an independent dataset or the test data itself. The latter is referred to as transcription-mode adaptation. We experimentally study the effect of these various parameters, and report on our findings.Keywords
This publication has 5 references indexed in Scilit:
- Acoustic adaptation using nonlinear transformations of HMM parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Robust speech recognition in noise using adaptation and mapping techniquesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A maximum-likelihood approach to stochastic matching for robust speech recognitionIEEE Transactions on Speech and Audio Processing, 1996
- A comparative study of speaker adaptation techniquesPublished by International Speech Communication Association ,1995
- A comparison of several approximate algorithms for finding multiple (N-best) sentence hypothesesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991