Lexical Access for Speech Understanding Using Minimum Message Length Encoding
Abstract
The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criterion for solving the Lexical Access Problem. We model sentences using phoneme realizations seen in training, and word and part-of-speech information obtained from text corpora. We show results on multiple-speaker, continuous, read speech and discuss a heuristic using equivalence classes of similar sounding words which speeds up the recognition process without significant deterioration in recognition accuracy.
Cite
Text
Thomas et al. "Lexical Access for Speech Understanding Using Minimum Message Length Encoding." Conference on Uncertainty in Artificial Intelligence, 1997.Markdown
[Thomas et al. "Lexical Access for Speech Understanding Using Minimum Message Length Encoding." Conference on Uncertainty in Artificial Intelligence, 1997.](https://mlanthology.org/uai/1997/thomas1997uai-lexical/)BibTeX
@inproceedings{thomas1997uai-lexical,
title = {{Lexical Access for Speech Understanding Using Minimum Message Length Encoding}},
author = {Thomas, Ian E. and Zukerman, Ingrid and Oliver, Jonathan J. and Albrecht, David W. and Raskutti, Bhavani},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {1997},
pages = {464-471},
url = {https://mlanthology.org/uai/1997/thomas1997uai-lexical/}
}