Ing. Lukáš Burget, Ph.D.

Karafiát, M., Grézl, F., Schwarz, P., Burget, L., Černocký, J.: Robust heteroscedastic linear discriminant analysis and LCRC posterior features in meeting data recognition, In: Proc. 3nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI 2006), Berlin, DE, Springer, 2006, s. 275-284, ISBN 3-540-69267-3
Jazyk publikace:angličtina
Název publikace:Robust heteroscedastic linear discriminant analysis and LCRC posterior features in meeting data recognition
Název (cs):Robustní heteroscedastická lineární dikriminační analýza a LCRC posteriorní příznaky v rozpoznávání meetingových dat
Strany:275-284
Sborník:Proc. 3nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI 2006)
Konference:3nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms
Řada knih:LNCS 4299
Místo vydání:Berlin, DE
Rok:2006
ISBN:3-540-69267-3
Vydavatel:Springer Verlag
URL:http://www.fit.vutbr.cz/~cernocky/publi/2006/karafiat_mlmi2006_honza.pdf [PDF]
Klíčová slova
speech recognition, feature extraction, acoustic modeling
Anotace
Článek pojednává o robustní heteroscedastická lineární dikriminační analýze a LCRC posteriorních příznacích v rozpoznávání meetingových dat
Abstrakt
This paper investigates into feature extraction for meeting recognition. Three robust variants of popular HLDA transform are investigated. Influence of adding posterior features to PLP feature stream is studied. The experimental results are obtained on two data-sets: CTS (continuous telephone speech) and meeting data from NIST RT'05 evaluations. Silence-reduced HLDA and LCRC phoneme-state posterior features are found to be suitable for both recognition tasks.
BibTeX:
@INPROCEEDINGS{
   author = {Martin Karafiát and František Grézl and Petr Schwarz and
	Lukáš Burget and Jan Černocký},
   title = {Robust heteroscedastic linear discriminant analysis and LCRC
	posterior features in meeting data recognition},
   pages = {275--284},
   booktitle = {Proc. 3nd Joint Workshop on Multimodal Interaction and
	Related Machine Learning Algorithms (MLMI 2006)},
   series = {LNCS 4299},
   year = {2006},
   location = {Berlin, DE},
   publisher = {Springer Verlag},
   ISBN = {3-540-69267-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=8236}
}

Vaše IPv4 adresa: 23.22.252.150
Přepnout na IPv6 spojení

DNSSEC [dnssec]