Publication Details

Probabilistic and bottle-neck features for LVCSR of meetings

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.
Czech title
Pravděpodobnostní a bottle-neck parametry pro LVCSR meetingů
Type
conference paper
Language
english
Authors
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Kontár Stanislav, Ing. (FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

Probabilistic features, bottle-neck features, TRAP-based features, LVCSR, meeting recognition

Abstract

The paper is about probabilistic and bottle-neck features for LVCSR of meetings

Annotation

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.

Published
2007
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), Honolulu, US
ISBN
1-4244-0728-1
Publisher
IEEE Signal Processing Society
Place
Hononulu, US
BibTeX
@INPROCEEDINGS{FITPUB8249,
   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 = "https://www.fit.vut.cz/research/publication/8249"
}
Back to top