Hierarchical Bayesian Language Models for Conversational Speech Recognition

Songfang Huang, S Renals
2010 IEEE Transactions on Audio, Speech, and Language Processing  
Traditional -gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfitting of maximum-likelihood estimation and the lack of rich contextual knowledge sources. In this paper, we exploit a hierarchical Bayesian interpretation for language modeling, based on a nonparametric prior called Pitman-Yor process. This offers a principled approach to language model smoothing, embedding the
more » ... edding the power-law distribution for natural language. Experiments on the recognition of conversational speech in multiparty meetings demonstrate that by using hierarchical Bayesian language models, we are able to achieve significant reductions in perplexity and word error rate.
doi:10.1109/tasl.2010.2040782 fatcat:44xd2wj57navvotw6yt3qcwayy