5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Context Dependent Tree Based Transforms For Phonetic Speech Recognition

Bernard Doherty, Saeed Vaseghi, Paul McCourt

The Queen's University of Belfast, Ireland

This paper presents a novel method for modeling phonetic context using linear context transforms. Initial investigations have shown the feasibility of synthesising context dependent models from context independent models through weighted interpolation of the peripheral states of a given hidden markov model with its adjacent model. This idea can be further extended, to maximum likelihood estimation of not only single weights, but a matrix of weights or a transform. This paper outlines the application of Maximum Likelihood Linear Regression (MLLR) as a means of modeling context dependency in continuous density Hidden Markov Models (HMM).

Full Paper

Bibliographic reference.  Doherty, Bernard / Vaseghi, Saeed / McCourt, Paul (1998): "Context dependent tree based transforms for phonetic speech recognition", In ICSLP-1998, paper 0323.