6 April 1995 Real-world speech recognition with neural networks
Author Affiliations +
Abstract
We describe a system based on neural networks that is designed to recognize speech transmitted through the telephone network. Context-dependent phonetic modeling is studied as a method of improving recognition accuracy, and a special training algorithm is introduced to make the training of these nets more manageable. Our system is designed for real-world applications, and we have therefore specialized our implementation for this goal; a pipelined DSP structure and a compact search algorithm are described as examples of this specialization. Preliminary results from a realistic test of the system (a field trial for the U.S. Census Bureau) are reported.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Etienne Barnard, Ronald Cole, Mark Fanty, Pieter J. E. Vermeulen, "Real-world speech recognition with neural networks", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); doi: 10.1117/12.205157; https://doi.org/10.1117/12.205157
PROCEEDINGS
14 PAGES


SHARE
Back to Top