Incorporating phonetic properties in hidden Markov models for speech recognition

Sitaram, Ramachandrula NV and Sreenivas, Thippur (1997) Incorporating phonetic properties in hidden Markov models for speech recognition. In: Journal of the Acoustical Society of America, 102 (2). pp. 1149-1158.

PDF Incorporating-312.pdf Restricted to Registered users only Download (236kB) | Request a copy

Abstract

In this paper the incorporation of important phonetic properties into hidden Markov models (HMM) is studied. Phones have characteristic properties such as unique temporal structure, context sensitive behavior and specific duration, etc. New HMMs which incorporate the above properties with additional degrees of freedom to the standard HMM states are proposed. The use of each of the phonetic property for speech recognition is demonstrated using the new HMMs. All the algorithms required for using these new models in various applications of speech recognition have been presented. Experimental comparison with the standard discrete HMM for a speaker-independent continuous speech phone recognition task show that consistent improvement is achieved by the new models.

Item Type:	Journal Article
Publication:	Journal of the Acoustical Society of America
Publisher:	Acoustical Society of America
Additional Information:	Copyright of this article belongs to Acoustical Society of America.
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	29 May 2007
Last Modified:	19 Sep 2010 04:35
URI:	http://eprints.iisc.ac.in/id/eprint/10045

Actions (login required)

View Item