Ústav počítačové grafiky a multimédií

Články na konferencích

Povey Daniel, Burget Lukáš, Agarwal Mohit, Akyazi Pinar, Feng Kai, Ghoshal Arnab, Glembek Ondřej, Goel Nagendra K., Karafiát Martin, Rastrow Ariya, Rose Richard, Schwarz Petr, Thomas Samuel: Subspace Gaussian mixture models for speech recognition, In: Proc. International Conference on Acoustics, Speech, and Signal Processing, Dallas, US, IEEESP, 2010, s. 4330-4333, ISBN 978-1-4244-4296-6, ISSN 1520-6149
Jazyk publikace:angličtina
Název publikace:Subspace Gaussian mixture models for speech recognition
Název (cs):Sub-space gaussovské modely pro rozpoznávání řeči
Strany:4330-4333
Sborník:Proc. International Conference on Acoustics, Speech, and Signal Processing
Konference:International Conference on Acoustics, Speech, and Signal Processing 2010
Místo vydání:Dallas, US
Rok:2010
ISBN:978-1-4244-4296-6
Časopis:Proc. International Conference on Acoustics, Speech, and Signal Processing, roč. 2010, č. 3, Piscataway, US
ISSN:1520-6149
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2010/povey_icassp2010_4330.pdf [PDF]
Klíčová slova
Speech Recognition, Hidden Markov Models, Gaussian Mixture Models
Anotace
Článek pojednává o sub-space gaussovských modelech pro rozpoznávání řeči. Popisujeme přístup akustického modelování, ve kterém všechny stavy fonetiky sdílejí stejnou gaussovskou strukturu.
Abstrakt
We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data.
BibTeX:
@INPROCEEDINGS{
   author = {Daniel Povey and Lukáš Burget and Mohit Agarwal and Pinar
	Akyazi and Kai Feng and Arnab Ghoshal and Ondřej Glembek and
	K. Nagendra Goel and Martin Karafiát and Ariya Rastrow and
	Richard Rose and Petr Schwarz and Samuel Thomas},
   title = {Subspace Gaussian mixture models for speech recognition},
   pages = {4330--4333},
   booktitle = {Proc. International Conference on Acoustics, Speech, and
	Signal Processing},
   journal = {Proc. International Conference on Acoustics, Speech, and
	Signal Processing},
   volume = {2010},
   number = {3},
   year = {2010},
   location = {Dallas, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4244-4296-6},
   ISSN = {1520-6149},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9311}
}

Vaše IPv4 adresa: 54.234.231.49
Přepnout na IPv6 spojení

DNSSEC [dnssec]