NonText Version

Speech Research Laboratory
AI. duPont Hospital for Children
and the
University of Delaware

SRL Main Page (text)

Info for Users (text)
Info for Clinicians (text)
Info for Researchers (text)

ModelTalker Speech Synthesizer

STAR: Speech Training, Assessment and Remediation (text)

Language and Speech

Newsletter (text)

Contact Us!


Research Info

HMM-based Phoneme Recognizer

This paper describes work on the development of an HMM-based system for automatic speech assessment, particularly of dysarthric speech. As a first step, we compare recognizer performance on a closed-set, forced choice identification test of dysarthric speech with performance on the same test by untrained listeners. Results indicate that HMM recognition accuracy averaged over all utterances of a dysarthric talker is well-correlated with measures of overall talker intelligibility. However, on an utterance-by-utterance basis, the pattern of errors obtained from the human subjects and the machine, while significantly correlated, accounts for, at best, only about 25 per cent of the variance. Potential methods for improving this performance are considered.

MenÚndez-Pidal, X., Polikoff, J.B., and Bunnell, H.T. (1997). "An HMM-based Phoneme Recognizer Applied to Assessment of Dysarthric Speech." Proceedings of EuroSpeech '97, September 22-25, 1997, Rhodes, Greece. [ps]

Projects | Publications | Related Links | Staff |
Facilities | Events | Positions