Efficient implementation of continuous speech recognition on a large scale parallel processor

This paper presents research into the use of large-scale parallelism for a continuous speech recognition algorithm. The algorithm, developed for the BBN Byblos system [1], uses context dependent Hidden-Markov models to achieve high recognition accuracy. The multiprocessor used in the research, the BBN Butterfly^TMParallel Processor, is a shared memory, MIMD machine. The algorithm was implemented using the Uniform System software methodology, a system that simplifies parallel programming without sacrificing efficiency. The algorithm is described, highlighting those portions critical to an efficient parallel implementation. Some of the problems encountered in trying to improve efficiency are presented as well as the solutions to those problems. The algorithm is shown to achieve 79% processor utilization on a 97-node Butterfly Parallel Processor. This is equivalent to a speedup by a factor of 77 over a single processor benchmark.