Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system
Lists
Only you see this
Abstract
We report on the results of the first evaluations for the BBN/LIMSI system under the new DARPA EARS program. The evaluations were carried out for conversational telephone speech (CTS) and broadcast news (BN) for three languages: English, Mandarin, and Arabic. In addition to providing system descriptions and evaluation results, the paper highlights methods that worked well across the two domains and those few that worked well on one domain but not the other. For the BN evaluations, which had to be run under 10 times real-time, we demonstrated that a joint BBN/LIMSI system with a time constraint achieved better results than either system alone.
BibTeX
@inproceedings{schwartz2004speech,
author = {Richard Schwartz and Thomas Colthurst and Nicolae Duta and H. Gish and Rishabh Iyer and C.-L. Kao and Dantong Liu and Owen Kimball and Ji Ma and J. Makhoul and Spyros Matsoukas and Long Nguyen and Mohamed Noamany and Ramjee Prasad and Beichen Xiang and D. Xu and J.-L. Gauvain and Lori Lamel and Holger Schwenk and Gilles Adda and L. Chen},
title = {{Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2004},
doi = {10.1109/icassp.2004.1326654},
}Loading related content...