First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Detection and Classification of Phonemes Using Context-Independent Error Back-Propagation

Hong C. Leung, James R. Glass, Michael S. Phillips, Victor W. Zue

Spoken Language Systems Group, Laboratory for Computer Science, Massachusetts Institute of Technology, Cambridge, USA

Over the past few years, we have been investigating the problem of utilizing artificial neural networks for phonetic classification. In this paper, we will describe several extensions to our earlier work, utilizing a segment-based approach. We will formulate our segmental framework and report our study on the use of multi-layer perceptions for detection and classification of phonemes. Issues related to computational requirements and input representations will also be discussed. Our investigation is performed within a set of experiments that attempts to recognize 38 vowels and consonants in American English independent of speaker. When evaluated on the TIMIT database, our system achieves an accuracy of 56%.

Full Paper

Bibliographic reference.  Leung, Hong C. / Glass, James R. / Phillips, Michael S. / Zue, Victor W. (1990): "Detection and classification of phonemes using context-independent error back-propagation", In ICSLP-1990, 1061-1064.