Large vocabulary speech recognition using a hidden Markov model for acoustic/phonetic classification

Author

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

Author_Institution

AT&T Bell Lab., Murray Hill, NJ, USA

fYear

1988

fDate

11-14 Apr 1988

Firstpage

505

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% word recognition was observed with the complete 52000 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%

Keywords

Markov processes; context-free grammars; speech analysis and processing; speech recognition; English grammar; acoustic processing; acoustic/phonetic classification; acoustic/phonetic decoder; fluent speech; hidden Markov model; isolated words; large vocabulary; lexical access mechanism; lexical processing; parser; phonetic processing; phonetic units; recognition rate; recognition tests; speech recognition system; syntax analysis; syntax analyzer; Acoustic testing; Feature extraction; Hidden Markov models; Lattices; Maximum likelihood decoding; Prediction methods; Speech analysis; Speech recognition; Vectors; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.196630

Filename

196630