5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Parallel Speech Recognition

Steven Phillips, Anne Rogers

AT&T Labs-Research, Florham Park, NJ, USA

Computer speech recognition has been very successful in limited domains and for isolated word recognition. However, widespread use of large-vocabulary continuous- speech recognizers is limited by the speed of current recognizers, which cannot reach acceptable error rates while running in real time. This paper shows how to harness shared memory multiprocessors, which are becoming increasingly common, to increase significantly the speed, and therefore the accuracy or vocabulary size, of a speech recognizer. We describe the parallelization of an existing high-quality speech recognizer, achieving a speedup of a factor of 3, 5 and 6 on 4, 8 and 12 processors respectively for the benchmark North American business news (NAB) recognition task.

Full Paper

Bibliographic reference.  Phillips, Steven / Rogers, Anne (1997): "Parallel speech recognition", In EUROSPEECH-1997, 135-138.