J. Lazzaro et J. Wawrzynek, SPEECH RECOGNITION EXPERIMENTS WITH SILICON AUDITORY MODELS, Analog integrated circuits and signal processing, 13(1-2), 1997, pp. 37-51
We have developed a real-time system to transform an audio signal into
several specialized representations of sound. The system uses analog
circuit models of biological audition to compute these representations
. We report on a speech recognizer that uses this system for feature e
xtraction, and we evaluate the performance of this speech recognition
system on a speaker-independent 13-word recognition task.