Conference paper

GRÉZL František, KARAFIÁT Martin, KONTÁR Stanislav and ČERNOCKÝ Jan. Probabilistic and bottle-neck features for LVCSR of meetings. In: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007). Hononulu: IEEE Signal Processing Society, 2007, pp. 757-760. ISBN 1-4244-0728-1.
Publication language:english
Original title:Probabilistic and bottle-neck features for LVCSR of meetings
Title (cs):Pravděpodobnostní a bottle-neck parametry pro LVCSR meetingů
Pages:757-760
Proceedings:Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007)
Conference:32nd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Place:Hononulu, US
Year:2007
ISBN:1-4244-0728-1
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2007/grezl_BN_fea_icassp_2007.pdf [PDF]
Keywords
Probabilistic features, bottle-neck features, TRAP-based features, LVCSR, meeting recognition
Annotation
The paper is about probabilistic and bottle-neck features for LVCSR of meetings
Abstract
In recent years, probabilistic features became an integral part of state-of-the-are LVCSR systems. In this work, we are exploring the possibility of obtaining the features directly from neural net without the necessity of converting output probabilities to features suitable for subsequent GMM-HMM system. We experimented with 5-layer MLP with bottle-neck in the middle layer. After training such a neural net, we used outputs of the bottle-neck as features for GMM-HMM recognition system. The benefits are twofold: first, improvement was gained when these features are used instead of the probabilistic features, second, the size of the system was reduced, as only part of the neural net is used. The experiments were performed on meetings recognition task defined in NIST RT'05 evaluation.
BibTeX:
@INPROCEEDINGS{
   author = {Franti{\v{s}}ek Gr{\'{e}}zl and Martin Karafi{\'{a}}t and
	Stanislav Kont{\'{a}}r and Jan {\v{C}}ernock{\'{y}}},
   title = {Probabilistic and bottle-neck features for LVCSR of meetings},
   pages = {757--760},
   booktitle = {Proc. IEEE International Conference on Acoustics, Speech and
	Signal Processing (ICASSP 2007)},
   year = {2007},
   location = {Hononulu, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {1-4244-0728-1},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=8249}
}

Your IPv4 address: 54.234.247.118
Switch to IPv6 connection

DNSSEC [dnssec]