In this paper, we describe the system designed and developed by team ELISA for DARPA’s LORELEI (Low Resource Languages for Emergent Incidents) pilot speech evaluation. The goal of the LORELEI program is to guide rapid resource deployment for humanitarian relief (e.g. for natural disasters), with a focus on “low-resource” language locations, where the cost of developing technologies for automated human language tools can be prohibitive both in monetary terms and timewise. In this phase of the program, the speech evaluation consisted of three separate tasks: detecting presence of an incident, classifying incident type, and classifying incident type along with identifying the location where it occurs. The performance metric was area under curve of precision-recall curves. Team ELISA competed against five other teams and won all the subtasks.
Cite as: Papadopoulos, P., Travadi, R., Vaz, C., Malandrakis, N., Hermjakob, U., Pourdamghani, N., Pust, M., Zhang, B., Pan, X., Lu, D., Lin, Y., Glembek, O., Baskar, M.K., Karafiát, M., Burget, L., Hasegawa-Johnson, M., Ji, H., May, J., Knight, K., Narayanan, S.S. (2017) Team ELISA System for DARPA LORELEI Speech Evaluation 2016. Proc. Interspeech 2017, 2053-2057, doi: 10.21437/Interspeech.2017-180
@inproceedings{papadopoulos17_interspeech,
author={Pavlos Papadopoulos and Ruchir Travadi and Colin Vaz and Nikolaos Malandrakis and Ulf Hermjakob and Nima Pourdamghani and Michael Pust and Boliang Zhang and Xiaoman Pan and Di Lu and Ying Lin and Ondřej Glembek and Murali Karthick Baskar and Martin Karafiát and Lukáš Burget and Mark Hasegawa-Johnson and Heng Ji and Jonathan May and Kevin Knight and Shrikanth S. Narayanan},
title={{Team ELISA System for DARPA LORELEI Speech Evaluation 2016}},
year=2017,
booktitle={Proc. Interspeech 2017},
pages={2053--2057},
doi={10.21437/Interspeech.2017-180}
}