The automatic recognition of stop consonants using hidden Markov models

Abstract

A speaker independent technique for identifying stops in continuous speech is described. The stops are modelled with continuous hidden Markov models (CHMM's) as consisting of several well defined segments; silence, voicing, a release and aspiration. These models are capable of performing two tasks. The first is the classification of an unknown stop and the second is to obtain a fine transcription of the stop into its segments. Features pertinent to stop recognition are obtained from the segment boundaries and are used together with the model scores in a non-parametric probability density function (pdf) estimator to identify the unknown stop consonants. A recognition rate of 84% was achieved on stops occurring in vowel-stop-vowel clusters that were taken from continuous speech.