A MRF-based parallel processing algorithm for speech recognition using linear predictive HMM

Author

Noda, Hideki ; Shirazi, Mehdi N.

Author_Institution

Commun. Res. Lab., Japan Ministry of Posts & Telecommun., Kobe, Japan

fYear

1994

fDate

19-22 Apr 1994

Abstract

Parallel processing in speech recognition is described, which is carried out at each frame on time axis. The authors have already proposed a parallel processing algorithm for HMM-based speech recognition using Markov random fields (MRF). The parallel processing is realized by modeling the hidden state sequence by an MRF and using the iterated conditional modes (ICM) algorithm to estimate the optimal state sequence given an observation sequence. However this parallel processing algorithm is applicable only to the standard HMM but not to the linear predictive HMM which takes into account the correlations between nearby observation vectors. The authors propose a parallel processing algorithm applicable to the correlation-considered HMM, where a new deterministic relaxation algorithm is used instead of the ICM algorithm for estimation of the optimal state sequence

Keywords

estimation theory; hidden Markov models; iterative methods; parallel algorithms; random processes; speech recognition; MRF-based parallel processing algorithm; Markov random fields; correlations; deterministic relaxation algorithm; hidden state sequence; iterated conditional modes; linear predictive HMM; nearby observation vectors; optimal state sequence; speech recognition; state sequence estimation; Concurrent computing; Hidden Markov models; Image processing; Laboratories; Markov random fields; Parallel processing; Speech recognition; State estimation; Vectors; Viterbi algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389223

Filename

389223