English

Lexical Access for Speech Understanding using Minimum Message Length Encoding

Computation and Language 2013-02-08 v1

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.

Keywords

Cite

@article{arxiv.1302.1572,
  title  = {Lexical Access for Speech Understanding using Minimum Message Length Encoding},
  author = {Ian Thomas and Ingrid Zukerman and Jonathan Oliver and David Albrecht and Bhavani Raskutti},
  journal= {arXiv preprint arXiv:1302.1572},
  year   = {2013}
}

Comments

Appears in Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI1997)

R2 v1 2026-06-21T23:22:12.615Z