Unsupervised Languagemodel Adaptation for Meeting Recognition
- 1 April 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-173-173
Abstract
We present an application of unsupervised language model (ML) adaptation to meeting recognition, in a scenario where sequences of multiparty meetings on related topics are to be recognized, but no prior in-domain data for LM training is available. The recognizer LMs are adapted according to the recognition output on temporally preceding meetings, either in speaker-dependent or speaker-independent mode. Model adaptation is carried out by interpolating the n-gram probabilities of a large generic LM with those of a small LM estimated from adaptation data, and minimizing perplexity on the automatic transcripts of a separate meeting set, also previously recognized. The adapted LMs yield about 5.9% relative reduction in word error compared to the baseline. This improvement is about half of what can be achieved with supervised adaptation, i.e. using human-generated speech transcripts.Keywords
This publication has 8 references indexed in Scilit:
- The Rich Transcription 2005 Spring Meeting Recognition Evaluation2006
- Unsupervised and active learning in automatic speech recognition for call classification2004
- Statistical language model adaptation: review and perspectivesSpeech Communication, 2004
- Unsupervised language model adaptation2003
- On-line learning of language models with word error probability distributions2002
- Maximum likelihood linear transformations for HMM-based speech recognitionComputer Speech & Language, 1998
- Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chainsIEEE Transactions on Speech and Audio Processing, 1994
- Improved clustering techniques for class-based statistical language modelling1993