EUROSPEECH '91
Second European Conference on Speech Communication and Technology

Genova, Italy
September 24-26, 1991

                 

Energy, Duration and Markov Models

P. Kenny, S. Parthasarathy, V. N. Gupta, Matthew Lennig, Paul Mermelstein, Douglas O'Shaughnessy

INRS-Telecorfimumcations, Montreal, Quebec, Canada

We present a new stochastic model for the energy and duration of phone segments ivhich takes account of the speech rate, the loudness of the signal and the effects of stress and pre-pausal lengthening and we show how the block Viterbi decoding algorithm can be used to integrate it with phone-based HMM speech recognizers. The model has been implemented on an isolated-word data-base and a preliminary experiment gives a modest improvement in word recognition accuracy.

Full Paper

Bibliographic reference.  Kenny, P. / Parthasarathy, S. / Gupta, V. N. / Lennig, Matthew / Mermelstein, Paul / O'Shaughnessy, Douglas (1991): "Energy, duration and Markov models", In EUROSPEECH-1991, 655-658.