First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

Enhancement and Optimisation of a Speech Recognition Front End Based on Hidden Markov Models

Fergus R. McInnes (1), Y. Ariki (2), Alan A. Wrench (1)

(1) Centre for Speech Technology Research, University of Edinburgh
(2) Department of Information Science, Faculty of Engineering, Kyoto University

A method for performance evaluation of the acoustic-phonetic front end of a continuous speech recognition system, using the entropy of its output, is described. Results are given for a front end based on phonemic hidden Markov models, with various optional enhancements which have been optimised using the entropy criterion.

Full Paper

Bibliographic reference.  McInnes, Fergus R. / Ariki, Y. / Wrench, Alan A. (1989): "Enhancement and optimisation of a speech recognition front end based on hidden Markov models", In EUROSPEECH-1989, 2461-2464.