Malay continuous speech recognition using fast HMM match algorithm

This paper describes the implementation of fast hidden Markov model (HMM) match algorithm in a phoneme-based Malay continuous speech recognition system. The decoding algorithm decouples the computations of state-likelihoods of phone HMM´s from the main search which is bounded by syntactical and lexical constraints. This avoids the redundant state-likelihood computations of identical phone HMM´s for different word models in the tightly integrated search and thus substantially reduce the decoding time. The algorithm is implemented in the framework of one pass dynamic programming search. For a 541-word task, the fast HMM match reduces the real-time factor (RTF) by a factor of 31.8 from 286.45 times RT to 9.02 times RT, compared to without decoupling. The word accuracy is maintained at 91.6% without loss for a test set perplexity of 15.45 in speaker-dependent mode.