Small-vocabulary speech recognition using surface electromyography

Authors:
Bradley J. Betts;Kim Binsted;Charles Jorgensen
Affiliations:
QSS Group Inc., NASA Ames Research Center, M/S 269-1, Moffett Field, CA 94035-1000, USA;NASA-UH Astrobiology Institute, Information and Computer Sciences Department, University of Hawaii, Post 317, 1680 East-West Road, Honolulu, HI 96744, USA;Neuro-Engineering Laboratory, NASA Ames Research Center, M/S 269-1, Moffett Field, CA 94035-1000, USA
Venue:
Interacting with Computers
Year:
2006

Citing 7
Cited 3

"Unvoiced speech recognition using EMG - mime speech recognition"

CHI '03 Extended Abstracts on Human Factors in Computing Systems
Gestures as Input: Neuroelectric Joysticks and Keyboards

IEEE Pervasive Computing
Web Browser Control Using EMG Based Sub Vocal Speech Recognition

HICSS '05 Proceedings of the Proceedings of the 38th Annual Hawaii International Conference on System Sciences - Volume 09
Neural Networks: A Comprehensive Foundation (3rd Edition)

Neural Networks: A Comprehensive Foundation (3rd Edition)
The Lombard effect: a reflex to better communicate with others in noise

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 04
Denoising of human speech using combined acoustic and EM sensor signal processing

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 01
Statistical voice activity detection using low-variance spectrum estimation and an adaptive threshold

IEEE Transactions on Audio, Speech, and Language Processing

Silent speech interfaces

Speech Communication
Speech interfaces based upon surface electromyography

Speech Communication
Brain-computer interfaces for speech communication

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present results of electromyographic (EMG) speech recognition on a small vocabulary of 15 English words. EMG speech recognition holds promise for mitigating the effects of high acoustic noise on speech intelligibility in communication systems, including those used by first responders (a focus of this work). We collected 150 examples per word of single-channel EMG data from a male subject, speaking normally while wearing a firefighter's self-contained breathing apparatus. The signal processing consisted of an activity detector, a feature extractor, and a neural network classifier. Testing produced an overall average correct classification rate on the 15 words of 74% with a 95% confidence interval of (71%, 77%). Once trained, the subject used a classifier as part of a real-time system to communicate to a cellular phone and to control a robotic device. These tasks were performed under an ambient noise level of approximately 95 decibels. We also describe ongoing work on phoneme-level EMG speech recognition.