ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Disordered speech recognition using acoustic and sEMG signals

Yunbin Deng, Rupal Patel, James T. Heaton, Glen Colby, L. Donald Gilmore, Joao Cabrera, Serge H. Roy, Carlo J. De Luca, Geoffrey S. Meltzner

Parallel isolated word corpora were collected from healthy speakers and individuals with speech impairment due to stroke or cerebral palsy. Surface electromyographic (sEMG) signals were collected for both vocalized and mouthed speech production modes. Pioneering work on disordered speech recognition using the acoustic signal, the sEMG signals, and their fusion are reported. Results indicate that speaker-dependent isolated-word recognition from the sEMG signals of articulator muscle groups during vocalized disorderedspeech production was highly effective. However, word recognition accuracy for mouthed speech was much lower, likely related to the fact that some disordered speakers had considerable difficulty producing consistent mouthed speech. Further development of the sEMG-based speech recognition systems is needed to increase usability and robustness.

doi: 10.21437/Interspeech.2009-227

Cite as: Deng, Y., Patel, R., Heaton, J.T., Colby, G., Gilmore, L.D., Cabrera, J., Roy, S.H., Luca, C.J.D., Meltzner, G.S. (2009) Disordered speech recognition using acoustic and sEMG signals. Proc. Interspeech 2009, 644-647, doi: 10.21437/Interspeech.2009-227

  author={Yunbin Deng and Rupal Patel and James T. Heaton and Glen Colby and L. Donald Gilmore and Joao Cabrera and Serge H. Roy and Carlo J. De Luca and Geoffrey S. Meltzner},
  title={{Disordered speech recognition using acoustic and sEMG signals}},
  booktitle={Proc. Interspeech 2009},