Automatic Speech Segmentation with Hmm

ABSTRACT: In this paper we review aspects of our automatic speech segmentation system that has been utilised in conjunction with our speech synthesis research. The speech segmentation system is based on a hidden Markov model phone recogniser using training strategies optimised for the segmentation task. Our research includes an analysis of the various aspects of the phone recogniser’s design and identifying the distinctions between paradigms of parameter estimation for speech segmentation and recognition. We also look at the limitations of HMM based segmentation and techniques for overcoming these limitations. The system evaluation demonstrates the ability of our system to provide high reliability speech segmentation that is comparable in performance to other state of the art systems.