Multi-Pattern Viterbi Algorithm for joint decoding of multiple speech patterns

Nair, Nishanth Ulhas and Sreenivas, TV (2010) Multi-Pattern Viterbi Algorithm for joint decoding of multiple speech patterns. In: Signal Processing, 90 (12). pp. 3278-3283.

PDF pattern.pdf - Published Version Restricted to Registered users only Download (349kB) | Request a copy

Abstract

Joint decoding of multiple speech patterns so as to improve speech recognition performance is important, especially in the presence of noise. In this paper, we propose a Multi-Pattern Viterbi algorithm (MPVA) to jointly decode and recognize multiple speech patterns for automatic speech recognition (ASR). The MPVA is a generalization of the Viterbi Algorithm to jointly decode multiple patterns given a Hidden Markov Model (HMM). Unlike the previously proposed two stage Constrained Multi-Pattern Viterbi Algorithm (CMPVA),the MPVA is a single stage algorithm. MPVA has the advantage that it cart be extended to connected word recognition (CWR) and continuous speech recognition (CSR) problems. MPVA is shown to provide better speech recognition performance than the earlier techniques: using only two repetitions of noisy speech patterns (-5 dB SNR, 10% burst noise), the word error rate using MPVA decreased by 28.5%, when compared to using individual decoding. (C) 2010 Elsevier B.V. All rights reserved.

Item Type:	Journal Article
Publication:	Signal Processing
Publisher:	Elsevier Science
Additional Information:	Copyright of this article belongs to Elsevier Science.
Keywords:	Joint decoding; ASR; Viterbi algorithm; MPVA; Multi-pattern.
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	08 Sep 2010 07:23
Last Modified:	19 Sep 2010 06:15
URI:	http://eprints.iisc.ac.in/id/eprint/32017

Actions (login required)

View Item