Various robust search methods in a Hungarian speech recognition system

Gosztolya, Gábor: Various robust search methods in a Hungarian speech recognition system. Acta cybernetica, (16) 2. pp. 229-240. (2003)

[img] Cikk, tanulmány, mű
cybernetica_016_numb_002_229-240.pdf

Download (687kB)

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.

Item Type: Article
Event Title: Conference for PhD Students in Computer Science, 3., 2002, Szeged
Journal or Publication Title: Acta cybernetica
Date: 2003
Volume: 16
Number: 2
Page Range: pp. 229-240
ISSN: 0324-721X
Language: angol
Uncontrolled Keywords: Természettudomány, Informatika
Additional Information: Bibliogr.: p. 239-240.; Abstract
Date Deposited: 2016. Oct. 15. 12:25
Last Modified: 2018. Apr. 10. 15:46
URI: http://acta.bibl.u-szeged.hu/id/eprint/12719

Actions (login required)

View Item View Item