Fast acoustic computations using graphics processors

Authors:
Paul R. Dixon;Tasuku Oonishi;Sadaoki Furui
Affiliations:
Department of Computer Science, Tokyo Institute of Technology, 2-12-1, Ookayama, Meguro-ku, Japan, 152-8552;Department of Computer Science, Tokyo Institute of Technology, 2-12-1, Ookayama, Meguro-ku, Japan, 152-8552;Department of Computer Science, Tokyo Institute of Technology, 2-12-1, Ookayama, Meguro-ku, Japan, 152-8552
Venue:
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year:
2009

Citing 0
Cited 5

Scalable HMM based inference engine in large vocabulary continuous speech recognition

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Opportunities and challenges of parallelizing speech recognition

HotPar'10 Proceedings of the 2nd USENIX conference on Hot topics in parallelism
A parallel meeting diarist

Proceedings of the 2010 international workshop on Searching spontaneous conversational speech
Language identification using multi-core processors

Computer Speech and Language
Fast Likelihood Computation in Speech Recognition using Matrices

Journal of Signal Processing Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a fast method for computing acoustic likelihoods that makes use of a Graphics Processing Unit (GPU). After enabling the GPU acceleration the main processor runtime dedicated to acoustic scoring tasks is reduced from the largest consumer to just a few percent even when using mixture models with a large number of Gaussian components. The results show a large reduction in decoding time with no change in accuracy and we also show by using a 16bit half precision floating point format for the acoustic model parameters, storage requirements can be halved with no reduction in accuracy.