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

Authors:
Nishanth Ulhas Nair;T. V. Sreenivas
Affiliations:
Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore 560012, India;Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore 560012, India
Venue:
Signal Processing
Year:
2010

Citing 4
Cited 0

Fundamentals of speech recognition

Fundamentals of speech recognition
A joint decoding algorithm for multiple-example-based addition of words to a pronunciation lexicon

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Joint evaluation of multiple speech patterns for speech recognition and training

Computer Speech and Language
Error bounds for convolutional codes and an asymptotically optimum decoding algorithm

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.08

Visualization

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 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 (-5dB SNR, 10% burst noise), the word error rate using MPVA decreased by 28.5%, when compared to using individual decoding.