Applications of Error Back-Propagation to Phonetic Classification

Abstract

This paper is concerced with the use of error back-propagation in phonetic classification. Our objective is to investigate the ba(cid:173) sic characteristics of back-propagation, and study how the frame(cid:173) work of multi-layer perceptrons can be exploited in phonetic recog(cid:173) nition. We explore issues such as integration of heterogeneous sources of information, conditioll~ that can affect performance of phonetic classification, internal representations, comparisons with traditional pattern classification techniques, comparisons of differ(cid:173) ent error metrics, and initialization of the network. Our investiga(cid:173) tion is performed within a set of experiments that attempts to rec(cid:173) ognize the 16 vowels in American English independent of speaker. Our results are comparable to human performance.

Cite

Text

Leung and Zue. "Applications of Error Back-Propagation to Phonetic Classification." Neural Information Processing Systems, 1988.

Markdown

[Leung and Zue. "Applications of Error Back-Propagation to Phonetic Classification." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/leung1988neurips-applications/)

BibTeX

@inproceedings{leung1988neurips-applications,
  title     = {{Applications of Error Back-Propagation to Phonetic Classification}},
  author    = {Leung, Hong C. and Zue, Victor W.},
  booktitle = {Neural Information Processing Systems},
  year      = {1988},
  pages     = {206-214},
  url       = {https://mlanthology.org/neurips/1988/leung1988neurips-applications/}
}