| Institute of Informatics>>> Acta Cybernetica>>> Past Issues>>> Volume 16, Number 2, 2003>>> |
 Magyarul
|
Various Robust Search Methods in a Hungarian Speech Recognition System
Gábor Gosztolya, András Kocsor, László Tóth, and László Felföldi
Abstract (in LaTeX format)
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.
Keywords: search methods, stack decoding, multi-stack decoding, Viterbi beam search.
Full text
Available electronic editions: PDF.
Note that full text is available only for papers that are at least 3 years old. For more recent papers only the first page of the paper is provided.
BibTeX entry
@article{Gosztolya:2003:ActaCybernetica,author = {G{\'a}bor Gosztolya and Andr{\'a}s Kocsor and L{\'a}szl{\'o} T{\'o}th and L{\'a}szl{\'o} Felf{\"o}ldi},
title = {Various Robust Search Methods in a Hungarian Speech Recognition System},
journal = {Acta Cybernetica},
year = {2003},
volume = {16},
number = {2},
pages = {229--240},
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.},
keywords = {search methods, stack decoding, multi-stack decoding, Viterbi beam search}
}