Back to search

Clemson University

Unsupervised Neural Pattern Classifiers for Oral Vowel Pronunciation of Foreign-Accented Speech

Abstract

dc:description.abstract

This thesis describes the development of unsupervised neural-based pattern classifiers for the training of vowel pronunciations for students learning a foreign language. This paper examines American learners of the French language. A corpus of single word utterances is compiled from a group of native French speakers. Cepstral features are used to train two unsupervised neural pattern classifiers: a self-organizing map and a growing neural gas. The development and justification for the use of these classifiers is presented. The output from the classifier is translated to a bar graph for visual assessment. The degree to which the utterance sounds native is determined by comparing target graphs and those produced by the user. It is concluded that unsupervised classification techniques can be used to develop a pronunciation training system that is independent of the language used to train the system. This allows for pronunciation training to be easily achieved for low-density languages.

Degree

thesis:*
Name thesis:degree_name
Master of Science (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Electrical Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Hecker, Joseph
Contributors dc:contributor
  • Gowdy, John N

Subjects

dc:subject × 5

Identifiers

dc:identifier.*
Repository record dc:identifier
https://open.clemson.edu/all_theses/24

Chain of custody

source
Harvested from
Clemson University
Base URL
open.clemson.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Hecker, Joseph. Unsupervised Neural Pattern Classifiers for Oral Vowel Pronunciation of Foreign-Accented Speech. Thesis thesis, https://open.clemson.edu/all_theses/24