Integrating Language Models with Speech Recognition (1994)
| Venue: | In Proceedings of the AAAI94 Workshop on the Integration of Natural Language and Speech Processing |
| Citations: | 11 - 5 self |
BibTeX
@INPROCEEDINGS{Harper94integratinglanguage,
author = {M.P. Harper and L.H. Jamieson and C.D. Mitchell and G. Ying and S. Potisuk and P.N. Srinivasan and R. Chen and C.B. Zoltowski and L. L. Mcpheters and B. Pellom and R. A. Helzerman},
title = {Integrating Language Models with Speech Recognition},
booktitle = {In Proceedings of the AAAI94 Workshop on the Integration of Natural Language and Speech Processing},
year = {1994},
pages = {pages}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
The question of how to integrate language models with speech recognition systems is becoming more important as speech recognition technology matures. For the purposes of this paper, we have classified the level of integration of current and past approaches into three categories: tightly-coupled, loosely-coupled, or semicoupled systems. We then argue that loose coupling is more appropriate given the current state of the art and given that it allows one to measure more precisely which components of the language model are most important. We will detail how the speech component in our approach interacts with the language model and discuss why we chose our language model. 1 Introduction State of the art speech recognition systems achieve high recognition accuracies only on tasks that have low perplexities. The perplexity of a task is, roughly speaking, the average number of choices at any decision point. The perplexity of a task is at a minimum when the true language model is known and co...
