Publication Details
Probabilistic and bottle-neck features for LVCSR of meetings
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Kontár Stanislav, Ing. (FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Probabilistic features, bottle-neck features, TRAP-based features, LVCSR, meeting recognition
The paper is about probabilistic and bottle-neck features for LVCSR of meetings
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.
@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"
}