Using Stress Information in Large Vocabulary Speech Recognition

Authors

  • Pierre Dumouchel
  • Matthew Lennig

Abstract

Using stress information in a Markov source-based large vocabulary speech recognition system provides a way to examine a nonlocal cue which, is generally poorly represented by the Markov source model. In this paper, we present an algorithm for estimating the stress pattern based on syllable durations and short-time energies. The output also gives the probability of the correctness of the estimated stress pattern. The parameters are first normalized in an attempt to reduce. variability due to different linguistic contexts. The stress pattern is then estimated based on a statistical approach. After initial training, tests on a new word list yielded 95% correct detection of the syllable carrying the primary stress. Finally. inclusion of this algorithm in a large vocabulary isolated word recognition system contributes to its accuracy.

Downloads

Published

2022-12-03

How to Cite

1.
Dumouchel P, Lennig M. Using Stress Information in Large Vocabulary Speech Recognition. Canadian Acoustics [Internet]. 2022 Dec. 3 [cited 2023 Feb. 8];14(3 bis):73-4. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3529

Issue

Section

Proceedings of the Acoustics Week in Canada