Bayesian learning for models of human speech perception

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Human speech recognition error rates are 30 times lower than machine error rates. Psychophysical experiments have pinpointed a number of specific human behaviors that may contribute to accurate speech recognition, but previous attempts to incorporate such behaviors into automatic speech recognition have often failed because the resulting models could not be easily trained from data. This paper describes Bayesian learning methods for computational models for human speech perception. Specifically, the linked computational models proposed in this paper seek to imitate the following human behaviors: independence of distinctive feature errors, perceptual magnet effect, the vowel sequence illusion, sensitivity to energy onsets and offsets, and redundant use of asynchronous acoustic correlates. The proposed models differ from many previous computational psychological models in that the desired behavior is learned from data, using a constrained optimization algorithm (the EM algorithm), rather than being coded into the model as a series of fixed rules.

Original languageEnglish (US)
Title of host publicationProceedings of the 2003 IEEE Workshop on Statistical Signal Processing, SSP 2003
PublisherIEEE Computer Society
Pages408-411
Number of pages4
ISBN (Electronic)0780379977
DOIs
StatePublished - 2003
Externally publishedYes
EventIEEE Workshop on Statistical Signal Processing, SSP 2003 - St. Louis, United States
Duration: Sep 28 2003Oct 1 2003

Publication series

NameIEEE Workshop on Statistical Signal Processing Proceedings
Volume2003-January

Other

OtherIEEE Workshop on Statistical Signal Processing, SSP 2003
Country/TerritoryUnited States
CitySt. Louis
Period9/28/0310/1/03

Keywords

  • Automatic speech recognition
  • Bayesian methods
  • Computational modeling
  • Error analysis
  • Humans
  • Mathematical model
  • Psychology
  • Signal processing algorithms
  • Speech processing
  • Speech recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Applied Mathematics
  • Signal Processing
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Bayesian learning for models of human speech perception'. Together they form a unique fingerprint.

Cite this