A method for the construction of acoustic Markov models for words

Author

Bahl, L.R. ; Brown, P.F. ; de Souza, P.V. ; Mercer, R.L. ; Picheny, M.A.

Author_Institution

Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA

Volume

1

Issue

4

fYear

1993

fDate

10/1/1993 12:00:00 AM

Firstpage

443

Lastpage

452

Abstract

A technique for constructing Markov models for the acoustic representation of words is described. Word models are constructed from models of subword units called fenones. Fenones represent very short speech events and are obtained automatically through the use of a vector quantizer. The fenonic baseform for a word-i.e., the sequence of fenones used to represent the word-is derived automatically from one or more utterances of that word. Since the word models are all composed from a small inventory of subword models, training for large-vocabulary speech recognition systems can be accomplished with a small training script. A method for combining phonetic and fenonic models is presented. Results of experiments with speaker-dependent and speaker-independent models on several isolated-word recognition tasks are reported. The results are compared with those for phonetics-based Markov models and template-based dynamic programming (DP) matching

Keywords

Markov processes; speech recognition; vector quantisation; acoustic Markov models; acoustic representation; fenones; isolated-word recognition; large-vocabulary speech recognition systems; phonetic models; small training script; speaker-dependent models; speaker-independent models; subword units; vector quantizer; word models; Degradation; Error analysis; Helium; Natural languages; Parameter estimation; Speech recognition; Training data; Vocabulary;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.242490

Filename

242490