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

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 (...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing Vol. 90; no. 12; pp. 3278 - 3283
Main Authors: Nair, Nishanth Ulhas, Sreenivas, T.V.
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.12.2010
Elsevier
Subjects:
Algorithms
Applied sciences
ASR
Bursting
Coding, codes
Decoding
Exact sciences and technology
Information, signal and communications theory
Joint decoding
Mathematical models
MPVA
Multi-pattern
Noise
Noise levels
Signal and communications theory
Signal processing
Speech
Speech processing
Speech recognition
Telecommunications and information theory
Viterbi algorithm
ASR
Joint decoding
MPVA
Viterbi algorithm
Multi-pattern
Performance evaluation
Multistage method
Probabilistic approach
Error rate
Decoding
Joint
Algorithm
Burst noise
Viterbi code
Hidden Markov models
Speech recognition
Automatic recognition
Speech processing
Signal to noise ratio
ISSN:0165-1684, 1872-7557
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 can 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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0165-1684
1872-7557
DOI:10.1016/j.sigpro.2010.05.006