Highly-Reverberant Real Environment database: HRRE
Audio and Speech Processing
2018-03-28 v2 Sound
Abstract
Speech recognition in highly-reverberant real environments remains a major challenge. An evaluation dataset for this task is needed. This report describes the generation of the Highly-Reverberant Real Environment database (HRRE). This database contains 13.4 hours of data recorded in real reverberant environments and consists of 20 different testing conditions which consider a wide range of reverberation times and speaker-to-microphone distances. These evaluation sets were generated by re-recording the clean test set of the Aurora-4 database which corresponds to five loudspeaker-microphone distances in four reverberant conditions.
Keywords
Cite
@article{arxiv.1801.09651,
title = {Highly-Reverberant Real Environment database: HRRE},
author = {Juan Pablo Escudero and Victor Poblete and José Novoa and Jorge Wuth and Josué Fredes and Rodrigo Mahu and Richard Stern and Néstor Becerra Yoma},
journal= {arXiv preprint arXiv:1801.09651},
year = {2018}
}
Comments
five pages