Large Vocabulary Speech Recognition using a Hidden Markov Model for Acoustic/Phonetic Classification

We report on our experiments with a new speech recognition system. The system comprises and acoustic/phonetic decoder, a lexical access mechanism and a syntax analyzer. The acoustic, phonetic and lexical processing are based on a continuously variable duration hidden Markov model (CVDHMM). The syntactic component is based on the Cocke-Kasami-Young (CKY) parser and a context free covering grammar of English.