LARGE VOCABULARY SPEECH RECOGNITION USING A HIDDEN MARKOV MODEL FOR ACOUSTIC/PHONETIC CLASSIFICATION.

S. E. Levinson, A. Ljolje, L. G. Miller

Research output: Contribution to journalConference articlepeer-review

Abstract

Experiments with a speech recognition system are reported. The system comprises an 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 content-free covering grammar of English. Lexical items are represented in terms of the 43 phonetic units. In recognition tests conducted on a separate data set, a 70% correct recognition rate on phonetic units in fluent speech was observed. In two additional tests on isolated words, a 40% correct word recognition was observed with the complete 52,000 word lexicon. When the vocabulary size was reduced to 1040 words, the recognition rate improved to 80%. After syntax analysis the word recognition rate rose to 90%.

Original languageEnglish (US)
Pages (from-to)505-508
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - Jan 1 1988
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'LARGE VOCABULARY SPEECH RECOGNITION USING A HIDDEN MARKOV MODEL FOR ACOUSTIC/PHONETIC CLASSIFICATION.'. Together they form a unique fingerprint.

Cite this