Physiological Sensors for Speech Recognition
Abstract
Systems designers are expressing greater interest in speech-based user interfaces for a variety of civilian and military applications. Such interfaces provide hands free operation and a more natural way for humans to interact with systems. One difficulty with speech-based user interfaces is poor operation in noisy environments such as military operations. The Physiological Sensor, developed at ARL, is an example of an alternative sensor for automatic speech recognition This sensor detects speech by measuring acoustic signals through the speaker's skin. While the signal produced is not typical of that from an airborne acoustic microphone, the possibility exists for using this sensor as a microphone. We investigate several possible methods for using the Physiological Sensor as a microphone for automatic speech recognition.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 12, 2002
- Accession Number
- ADP014015
Entities
People
- Francis Fisher
- Mike Scanlon
- Steve Chen
Organizations
- United States Army Research Laboratory