5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

On the Influence of the Delta Coefficients in a HMM-based Speech Recognition System

Fabrice Lefevre, Claude Montacie, Marie-Josť Caraty

LIP6, France

The delta coefficients are a conventional method to include temporal information in the speech recognition systems. In particular, they are widely used in the gaussian HMM-based systems. Some attempts were made to introduce the delta coefficients in the K-Nearest Neighbours (K-NN) HMM-based system that we recently developed. An introduction of the delta coefficients directly in the representation space is shown not to be suitable with the K-NN probability density function (pdf) estimator. So, we investigate whether the delta coefficient could be used to improve the K-NN HMM-based system in other ways. In this purpose, an analysis of the delta coefficients in the gaussian HMM-based systems is proposed. It leads to the conclusion that the delta coefficients influence also the recognition process.

Full Paper

Bibliographic reference.  Lefevre, Fabrice / Montacie, Claude / Caraty, Marie-Josť (1998): "On the influence of the delta coefficients in a HMM-based speech recognition system", In ICSLP-1998, paper 0573.