This paper describes a simple and robust method for improving the runtime of likelihood computation on multi-core processors without degrading system accuracy. The method improves runtime by parallelizing likelihood computations on a multi-core processor. Mixtures are decomposed among the cores and each core computes the likelihood of the mixture allocated to it. We study two approaches to mixture decomposition Chunk based and Decisiontree based. When applied to RWTH TC-STAR EPPS English LVCSR system on an Intel Core2 Quad processor with varying pruningbeam width settings, the method resulted in a 54% to 70% improvement in the likelihood computation runtime, and a 18% to 59% improvement in the overall runtime.
Cite as: Parihar, N., Schlüter, R., Rybach, D., Hansen, E.A. (2009) Parallel fast likelihood computation for LVCSR using mixture decomposition. Proc. Interspeech 2009, 3047-3050, doi: 10.21437/Interspeech.2009-565
@inproceedings{parihar09_interspeech,
author={Naveen Parihar and Ralf Schlüter and David Rybach and Eric A. Hansen},
title={{Parallel fast likelihood computation for LVCSR using mixture decomposition}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={3047--3050},
doi={10.21437/Interspeech.2009-565}
}