Huang, Songfang

Renals, Steve

2010-12-15T13:57:33Z

2010-12-15T13:57:33Z

2010

2010-12-15T13:57:33Z

Traditional n-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 the Pitman--Yor process. This offers a principled approach to language model smoothing, embedding 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.

1941--1954

10.1109/TASL.2010.2040782

http://dx.doi.org/10.1109/TASL.2010.2040782

http://hdl.handle.net/1842/4528

IEEE

Hierarchical Bayesian Language Models for Conversational Speech Recognition

Article

8

IEEE Transactions on Audio, Speech and Language Processing

18