Understanding speech played back in noisy and reverberant conditions remains a challenging task. This paper describes the Hurricane Challenge 2.0, the second large-scale evaluation of algorithms aiming to solve the near-end listening enhancement problem. The challenge consisted of modifying German, English, and Spanish speech, which was then evaluated by a total of 187 listeners at three sites. Nine algorithms participated in the challenge. Results indicate a large variability in performance between the algorithms, and that some entries achieved large speech intelligibility benefits. The largest observed benefits corresponded to intensity changes of about 7 dB, which exceeded the results obtained in the previous challenge despite more complex listening conditions. A priori information about the acoustic conditions did not provide a general advantage.
Cite as: Rennies, J., Schepker, H., Valentini-Botinhao, C., Cooke, M. (2020) Intelligibility-Enhancing Speech Modifications — The Hurricane Challenge 2.0. Proc. Interspeech 2020, 1341-1345, doi: 10.21437/Interspeech.2020-1641
@inproceedings{rennies20_interspeech, author={Jan Rennies and Henning Schepker and Cassia Valentini-Botinhao and Martin Cooke}, title={{Intelligibility-Enhancing Speech Modifications — The Hurricane Challenge 2.0}}, year=2020, booktitle={Proc. Interspeech 2020}, pages={1341--1345}, doi={10.21437/Interspeech.2020-1641} }