Článek ve sborníku konference

 
Grézl, F., Karafiát, M.: Integrating recent MLP feature extraction techniques into TRAP architecture, In: Proceedings of Interspeech 2011, Florence, IT, ISCA, 2011, s. 1229-1232, ISBN 978-1-61839-270-1, ISSN 1990-9772
Jazyk publikace:angličtina
Název publikace:Integrating recent MLP feature extraction techniques into TRAP architecture
Název (cs):Integrace moderních technik extrakce příznaků pomocí MLP do TRAP architektury
Strany:1229-1232
Sborník:Proceedings of Interspeech 2011
Konference:Interspeech 2011
Místo vydání:Florence, IT
Rok:2011
ISBN:978-1-61839-270-1
Časopis:Proceedings of Interspeech, roč. 2011, č. 8, FR
ISSN:1990-9772
Vydavatel:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/grezl_interspeech2011_204.pdf [PDF]
Klíčová slova
TRAP processing, Bottle-Neck technique, subphoneme classes, LVCSR features
Anotace
Článek ukazuje zlepšení ale i limity TRAP a HATS systémů pro extrakci příznaků pro automatické rozpoznávání řeči s velkým slovníkem při použití Bottle-Neck techniky a fonémových stavů pro trénování neuronových sítí.
Abstrakt
This paper is focused on the incorporation of recent techniques for multi-layer perceptron (MLP) based feature extraction in Temporal Pattern (TRAP) and Hidden Activation TRAP (HATS) feature extraction scheme. The TRAP scheme has been origin of various MLP-based features some of which are now indivisible part of state-of-the-art LVCSR systems. The modifications which brought most improvement - sub-phoneme targets and Bottle-Neck technique - are introduced into original TRAP scheme. Introduction of sub-phoneme targets uncovered the hidden danger of having too many classes in TRAP/HATS scheme. On the other hand, Bottle-Neck technique improved the TRAP/HATS scheme so its competitive with other approaches.
BibTeX:
@INPROCEEDINGS{
   author = {František Grézl and Martin Karafiát},
   title = {Integrating recent MLP feature extraction techniques into
	TRAP architecture},
   pages = {1229--1232},
   booktitle = {Proceedings of Interspeech 2011},
   journal = {Proceedings of Interspeech},
   volume = {2011},
   number = {8},
   year = {2011},
   location = {Florence, IT},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-61839-270-1},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9755}
}