Various robust search methods in a Hungarian speech recognition system

Authors:
Gábor Gosztolya;András Kocsor;László Tóth;László Felföldi
Affiliations:
Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged, H-6720 Szeged, Aradi vértanúk tere 1., Hungary;Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged, H-6720 Szeged, Aradi vértanúk tere 1., Hungary;Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged, H-6720 Szeged, Aradi vértanúk tere 1., Hungary;Department of Informatics, University of Szeged H-6720 Szeged, Arpád tér 2., Hungary
Venue:
Acta Cybernetica
Year:
2003

Citing 3
Cited 0

Statistical methods for speech recognition

Statistical methods for speech recognition
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Correction to "A Formal Basis for the Heuristic Determination of Minimum Cost Paths"

ACM SIGART Bulletin

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work focuses on the search aspect of speech recognition. We describe some standard algorithms such as stack decoding, multi-stack decoding, the Viterbi beam search and an A* heuristic, then present improvements on these search methods. Finally we compare the performance of each algorithm, grading them according to their performance. We will show that our improvements can outperform the standard methods.