Sub auditory speech recognition based on EMG signals
Jorgensen, C.
Lee, D.D.
Agabont, S.
Computational Sci. Div., NASA Ames Res. Center, Moffett Field, CA, USA;
This paper appears in: Neural Networks, 2003. Proceedings of the International Joint Conference on
Publication Date: 20-24 July 2003
Volume: 4,
On page(s): 3128- 3133 vol.4
ISSN: 1098-7576
ISBN: 0-7803-7898-9
INSPEC Accession Number: 8597215
Digital Object Identifier: 10.1109/IJCNN.2003.1224072
Current Version Published: 2003-08-26
Abstract
Sub acoustic electromyogram (EMG) signal classification is demonstrated as a method for silent speech recognition. Recorded electrode signals from the larynx and sublingual areas below the jaw are noise filtered and transformed into features using complex dual quad tree wavelet transforms. Feature sets for six sub acoustically pronounced words are trained using a trust region scaled conjugate gradient neural network. Real time signals for previously unseen patterns are classified into categories suitable for primitive control of graphic objects. Feature construction, recognition accuracy and an approach for extension of the technique to a variety of real world application areas are presented.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
