Paper

Extracting binary features from speech production errors and perceptual confusions using Redundancy-Corrected Transmission

Authors
  • Zhanao Fu (University of Toronto)
  • Ewan Dunbar (University of Toronto)

Abstract

We develop a mutual information-based feature extraction method and apply it to English speech production and perception error data. The extracted features show different phoneme groupings than conventional phonological features, especially in the place features. We evaluate how well the extracted features can define natural classes to account for English phonological patterns. The features extracted from production errors had performance close to conventional phonological features, while the features extracted from perception errors performed worse. The study shows that featural information can be extracted from underused sources of data such as confusion matrices of production and perception errors, and the results suggest that phonological patterning is more closely related to natural production errors than to perception errors in noisy speech.

Keywords: Feature Extraction, Phonology, Speech Error, Production, Perception

How to Cite:

Fu, Z. & Dunbar, E., (2023) “Extracting binary features from speech production errors and perceptual confusions using Redundancy-Corrected Transmission”, Society for Computation in Linguistics 6(1), 95-107. doi: https://doi.org/10.7275/1d83-fs47

Downloads:
Download PDF

86 Views

31 Downloads

Published on
01 Jun 2023