A parallel implementation of a hidden Markov model with duration modeling for speech recognition

Author

Mitchell, Carl D. ; Helzerman, Randall A. ; Jamieson, Leah H. ; Harper, Mary P.

Author_Institution

Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA

fYear

1993

fDate

1-4 Dec 1993

Firstpage

298

Lastpage

306

Abstract

This paper describes a parallel implementation of a Hidden Markov Model (HMM) for spoken language recognition on the MasPar MP-1. By exploiting the massive parallelism of explicit duration HMMs, we can develop more complex models for real-time speech recognition. Implementational issues such as choice of data structures, method of communication, and utilization of parallel functions are explored. The results of our experiments show that the parallelism in HMMs can be effectively exploited by the MP-1. Training that use to take nearly a week can now be completed in about an hour. The system can recognize the phones of a test utterance in a fraction of a second

Keywords

computational complexity; hidden Markov models; parallel algorithms; speech recognition; MasPar MP-1; data structures; duration modeling; hidden Markov model; parallel implementation; real-time speech recognition; spoken language recognition; Automatic speech recognition; Computational efficiency; Costs; Data structures; Hidden Markov models; Natural languages; Neodymium; Parallel processing; Speech recognition; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel and Distributed Processing, 1993. Proceedings of the Fifth IEEE Symposium on

Conference_Location

Dallas, TX

Print_ISBN

0-8186-4222-X

Type

conf

DOI

10.1109/SPDP.1993.395519

Filename

395519