Hierarchical Pitman-Yor language models for ASR in meetings (2007)
| Venue: | In Proceedings of IEEE ASRU International Conference |
| Citations: | 6 - 3 self |
BibTeX
@INPROCEEDINGS{Huang07hierarchicalpitman-yor,
author = {Songfang Huang and Steve Renals},
title = {Hierarchical Pitman-Yor language models for ASR in meetings},
booktitle = {In Proceedings of IEEE ASRU International Conference},
year = {2007},
pages = {124--129}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper we investigate the application of a hierarchical Bayesian language model (LM) based on the Pitman-Yor process for automatic speech recognition (ASR) of multiparty meetings. The hierarchical Pitman-Yor language model (HPY-LM) provides a Bayesian interpretation of LM smoothing. An approximation to the HPYLM recovers the exact formulation of the interpolated Kneser-Ney smoothing method in n-gram models. This paper focuses on the application and scalability of HPYLM on a practical large vocabulary ASR system. Experimental results on NIST RT06s evaluation meeting data verify that HPYLM is a competitive and promising language modeling technique, which consistently performs better than interpolated Kneser-Ney and modified Kneser-Ney n-gram LMs in terms of both perplexity and word error rate.
