Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)
Hong Leung, James Glass, Michael Phillips, Victor W. Zue
In this paper, we will describe several extensions to our earlier work, utiliz(cid:173) ing a segment-based approach. We will formulate our segmental framework and report our study on the use of multi-layer perceptrons for detection and classification of phonemes. We will also examine the outputs of the network, and compare the network performance with other classifiers. 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%.