Automatic speech recognition with sparse training data for dysarthric speakers.
作者： Pam Enderby , Mark S. Hawley , Phil D. Green , James Carmichael , Athanassios Hatzis
DOI:
关键词:
摘要: We describe an unusual ASR application: recognition of command words from severely dysarthric speakers, who have poor control their articulators. The goal is to allow these clients assistive technology by voice. While this a small vocabulary, speaker-dependent, isolated-word application, the speech material more variable than normal, and only amount data available for training. After training CDHMM recogniser, it necessary predict its likely performance without using independent test set,so that confusable can be replaced alternatives. present battery measures consistency confusability, based on forced-alignment, which used recogniser performance. show how perform, they are presented clinicians users system.
isca-speech.org参考文章(13)
Phil D. Green, Athanassios Hatzis, S. J. Howard, Optical logo-therapy (OLT): a computer-based real time visual feedback application for speech training. conference of the international speech communication association. ,(1997)
Phil D. Green, Rebecca Palmer, James Carmichael, Athanassios Hatzis, Mark Parker, Peter O'Neill, Stuart P. Cunningham, An integrated toolkit deploying speech technology for computer based speech training with application to dysarthric speakers. conference of the international speech communication association. ,(2003)
Pamela M. Enderby, Joyce Emerson, Does speech and language therapy work? : a review of the literature Whurr. ,(1995)
Bronagh Blaney, John Wilson, Acoustic variability in dysarthria and computer speech recognition Clinical Linguistics & Phonetics. ,vol. 14, pp. 307- 327 ,(2000) , 10.1080/02699200050024001
J.R. Deller, D. Hsu, L.J. Ferrier, On the use of hidden Markov modelling for recognition of Dysarthric speech Computer Methods and Programs in Biomedicine. ,vol. 35, pp. 125- 139 ,(1991) , 10.1016/0169-2607(91)90071-Z
Ava-Lee Kotler, Nancy Thomas-Stonell, Effects of speech training on the accuracy of speech recognition for an individual with a speech impairment Augmentative and Alternative Communication. ,vol. 13, pp. 71- 80 ,(1997) , 10.1080/07434619712331277858
Linda Ferrier, Howard Shane, Holly Ballard, Tyler Carpenter, Anne Benoit, Dysarthric speakers' intelligibility and speech characteristics in relation to computer speech recognition Augmentative and Alternative Communication. ,vol. 11, pp. 165- 175 ,(1995) , 10.1080/07434619512331277289
Kristin Rosen, Sasha Yampolsky, Automatic speech recognition and a review of its functioning with dysarthric speech Augmentative and Alternative Communication. ,vol. 16, pp. 48- 60 ,(2000) , 10.1080/07434610012331278904
L.R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition Proceedings of the IEEE. ,vol. 77, pp. 267- 296 ,(1989) , 10.1109/5.18626
Nancy Thomas-Stonell, Ava-Lee Kotler, Herbert Leeper, Philip Doyle, Computerized speech recognition: influence of intelligibility and perceptual consistency on recognition accuracy Augmentative and Alternative Communication. ,vol. 14, pp. 51- 56 ,(1998) , 10.1080/07434619812331278196