Title :
Learning and Plan Refinement in a Knowledge-Based System for Automatic Speech Recognition
Author :
de Mori, Renato ; Lam, Lily ; Gilloux, Michel
Author_Institution :
School of Computer Science, McGill University, Montreal, P. Q. H3A 2K6, Canada.
fDate :
3/1/1987 12:00:00 AM
Abstract :
This paper shows how a semiautomatic design of a speech recognition system can be done as a planning activity. Recognition performances are used for deciding plan refinement. Inductive learning is performed for setting action preconditions. Experimental results in the recognition of connected letters spoken by 100 speakers are presented.
Keywords :
Automatic speech recognition; Computer science; Decoding; Knowledge based systems; Loudspeakers; Pattern matching; Prototypes; Speech recognition; Stochastic processes; Vocabulary; Automatic speech recognition; connected speech recognition; inductive learning; letter recognition; network of actions; planning; stochastic rules;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1987.4767902
