On blocking matrix-based dereverberation for automatic speech recognition

Conference contribution
(Conference Contribution)

Publication Details

Author(s): Schwarz A, Reindl K, Kellermann W
Publication year: 2012
Pages range: 1-4
ISBN: 9783800734511
Language: English


We investigate a two-channel reverberation suppression scheme comprising a blocking matrix for estimating late reverberation components by canceling the direct path and early reflections, and spectral enhancement filters for suppressing the late reverberation components. For idealized blocking matrices, we analyze the influence of the length of the blocking matrix filters and the impact of the coherence between the microphones on the resulting estimate. We show that blocking matrices that cancel more than the direct path of the desired signal can be of advantage for robust speech recognition in highly reverberant environments.

FAU Authors / FAU Editors

Kellermann, Walter Prof. Dr.-Ing.
Professur für Nachrichtentechnik
Reindl, Klaus
Professur für Nachrichtentechnik
Schwarz, Andreas
Professur für Nachrichtentechnik

How to cite

Schwarz, A., Reindl, K., & Kellermann, W. (2012). On blocking matrix-based dereverberation for automatic speech recognition. (pp. 1-4). Aachen, DE.

Schwarz, Andreas, Klaus Reindl, and Walter Kellermann. "On blocking matrix-based dereverberation for automatic speech recognition." Proceedings of the International Workshop on Acoustic Signal Enhancement (IWAENC), Aachen 2012. 1-4.


Last updated on 2018-17-10 at 09:38