1000-word speaker-independent continuous-speech recognition using hidden Markov models

Author

Murviet, H. ; Weintraub, Mitchel

Author_Institution

SRI Int., Menlo Park, CA, USA

fYear

1988

fDate

11-14 Apr 1988

Firstpage

1115

Abstract

An algorithm based on hidden Markov models is applied to the task of speaker-independent continuous-speech recognition for a vocabulary of 1000 words with no syntactic constraints. The signal is limited to 4000 Hz. Word models were built from three-state representations of phonetic units, concatenated according to entries in a lexicon. Performance as measured on DARPAs resource management database was 40% correct word recognition. It was found that the use of several different acoustic features and the use of word-specific phonetic modeling, where possible, improved system performance

Keywords

Markov processes; database management systems; speech recognition; 4000 Hz; acoustic features; hidden Markov models; lexicon; phonetic units; resource management database; speaker-independent continuous-speech recognition; syntactic constraints; word recognition; word-specific phonetic modeling; Decoding; Feature extraction; Finite impulse response filter; Hidden Markov models; Parameter estimation; Spatial databases; Speech analysis; Speech recognition; Training data; 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.1988.196525

Filename

196525