Parallel fast likelihood computation for LVCSR using mixture decomposition

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 Decision-tree based. When applied to RWTH TC-STAR EPPS English LVCSR system on an Intel Core2 Quad processor with varying pruning-beam 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.