Automatic Speech Recognition for Resource Constrained Embedded Systems

The design and implementation of prototype hardware/software architecture for automatic single word speech recognition on resource-constrained embedded devices Designed as a voice-activated extension of an existing wireless nurse call system, their prototype device continually listens for a pre-recorded keyword and uses speech recognition techniques to trigger an alert upon detecting a match. Preliminary experiments show that their prototype achieves a high average detection rate of 96%, while only dissipating 28.5mW for continuous audio sampling and duty-cycled speech recognition.

Provided by: International Journal of Scientific Engineering and Technology Research (IJSETR) Topic: Enterprise Software Date Added: Sep 2015 Format: PDF

Find By Topic