Adaptive language models for spoken dialogue systems (2002)
| Venue: | in Proceedings of the ICASSP |
| Citations: | 7 - 0 self |
BibTeX
@INPROCEEDINGS{Solsona02adaptivelanguage,
author = {Roger Argiles Solsona and Eric Fosler-lussier and Hong-kwang J. Kuo and Ros Potamianos and Imed Zitouni},
title = {Adaptive language models for spoken dialogue systems},
booktitle = {in Proceedings of the ICASSP},
year = {2002}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper, we investigate both generative and statistical approaches for language modeling in spoken dialogue systems. Semantic class-based finite state ¢ and-gram grammars are used for improving coverage and modeling accuracy when little training data is available. We have implemented dialogue-state specific language model adaptation to reduce perplexity and improve the efficiency of grammars for spoken dialogue systems. A novel algorithm for state-independent ¢ combining-gram and state-dependent finite state grammars using acoustic confidence scores is proposed. Using this combination strategy, a relative word error reduction of 12 % is achieved for certain dialogue states within a travel reservation task. Finally, semantic class multigrams are proposed and briefly evaluated for language modeling in dialogue systems. 1.
