A parallel phoneme recognition algorithm based on continuous hidden Markov model

Author

Chung, Sang-Hwa ; Park, Min-Uk ; Kim, Hyung-Soon

Author_Institution

Dept. of Comput. Eng., Pusan Nat. Univ., South Korea

fYear

1999

fDate

12-16 Apr 1999

Firstpage

453

Lastpage

457

Abstract

This paper presents a parallel phoneme recognition algorithm based on the continuous Hidden Markov Model (HMM). The parallel phoneme recognition algorithm distributes 3-state HMMs of context dependent phonemes to the multiprocessors, computes output probabilities in parallel, and enhances the Viterbi beam search with a message passing mechanism. The algorithm is implemented in a multi-transputer system using distributed-memory MIMD multiprocessors. Experimental results show the feasibility of the parallel phoneme recognition algorithm in constructing a real-time parallel speech recognition system based on time-consuming continuous HMM

Keywords

hidden Markov models; parallel algorithms; speech recognition; Hidden Markov Model; Viterbi beam search; message passing mechanism; output probabilities; parallel phoneme recognition algorithm; phoneme recognition; Concurrent computing; Context modeling; Covariance matrix; Hidden Markov models; Probability; Read only memory; Speech; Stochastic processes; Topology; Viterbi algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel Processing, 1999. 13th International and 10th Symposium on Parallel and Distributed Processing, 1999. 1999 IPPS/SPDP. Proceedings

Conference_Location

San Juan

Print_ISBN

0-7695-0143-5

Type

conf

DOI

10.1109/IPPS.1999.760516

Filename

760516