TY - GEN
T1 - Sentence recognition from articulatory movements for silent speech interfaces
AU - Wang, Jun
AU - Samal, Ashok
AU - Green, Jordan R.
AU - Rudzicz, Frank
PY - 2012
Y1 - 2012
N2 - Recent research has demonstrated the potential of using an articulation-based silent speech interface for command-and-control systems. Such an interface converts articulation to words that can then drive a text-to-speech synthesizer. In this paper, we have proposed a novel near-time algorithm to recognize whole-sentences from continuous tongue and lip movements. Our goal is to assist persons who are aphonic or have a severe motor speech impairment to produce functional speech using their tongue and lips. Our algorithm was tested using a functional sentence data set collected from ten speakers (3012 utterances). The average accuracy was 94.89% with an average latency of 3.11 seconds for each sentence prediction. The results indicate the effectiveness of our approach and its potential for building a real-time articulation-based silent speech interface for clinical applications.
AB - Recent research has demonstrated the potential of using an articulation-based silent speech interface for command-and-control systems. Such an interface converts articulation to words that can then drive a text-to-speech synthesizer. In this paper, we have proposed a novel near-time algorithm to recognize whole-sentences from continuous tongue and lip movements. Our goal is to assist persons who are aphonic or have a severe motor speech impairment to produce functional speech using their tongue and lips. Our algorithm was tested using a functional sentence data set collected from ten speakers (3012 utterances). The average accuracy was 94.89% with an average latency of 3.11 seconds for each sentence prediction. The results indicate the effectiveness of our approach and its potential for building a real-time articulation-based silent speech interface for clinical applications.
KW - Sentence recognition
KW - laryngectomy
KW - silent speech interface
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=84867591892&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867591892&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2012.6289039
DO - 10.1109/ICASSP.2012.6289039
M3 - Conference contribution
AN - SCOPUS:84867591892
SN - 9781467300469
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4985
EP - 4988
BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Y2 - 25 March 2012 through 30 March 2012
ER -