Hierarchical Bayesian Language Models for Conversational Speech Recognition

@article{Huang2010HierarchicalBL,
  title={Hierarchical Bayesian Language Models for Conversational Speech Recognition},
  author={Songfang Huang and Steve Renals},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2010},
  volume={18},
  pages={1941-1954}
}
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 Pitman-Yor process. This offers a principled approach to language model smoothing, embedding the power… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 21 CITATIONS

Similar Papers

Loading similar papers…