Experimental evaluation of segmental HMMs

Abstract

The aim of the research described is to overcome important speech-modeling limitations of conventional hidden Markov models (HMMs), by developing a dynamic segmental HMM which models the changing pattern of speech over the duration of some phoneme-type unit. As a first step towards this goal, a static segmental HMM has been implemented and tested. This model reduces the influence of the independence assumption by using two processes to model variability due to long-term factors separately from local variability that occurs within a segment. Experiments have demonstrated that the performance of segmental HMMs relative to conventional HMMs is dependent on the quality of the system in which they are embedded. On a connected-digit recognition task for example, static segmental HMMs outperformed conventional HMMs for triphone systems but not for a vocabulary-independent monophone system. It is concluded that static segmental HMMs improve performance, as long as the system is such that the independence assumption is a major limiting factor.