Summary: INTEGRATING NEURAL NETWORKS INTO COMPUTER SPEECH RECOGNITION SYSTEMS
Michael Cohen*, Horacio Franco*, Nelson Morgan**, David Rumelhart***,
Victor Abrash*, and Yochai Konig**
5
*
* Speech Research Program, SRI International, Menlo Park, CA 9402
* Intl. Computer Science Inst., 1947 Center Street, Suite 600, Berkeley, CA 94704
test
*** Stanford University, Dept. of Psychology, Stanford, CA 94305
1. Introduction
n
s
Most current state­of­the­art continuous­speech recognitio
ystems are based on hidden Markov modeling techniques.
i
The work described here involved integrating neural networks
nto a hidden Markov model­based state­of­the­art
m
continuous­speech recognition system, resulting in improve­
ents in recognition accuracy and reductions in model com­

Source: Abrash, Victor - Speech Technology & Research Laboratory, SRI International

Collections: Computer Technologies and Information Sciences