On blocking matrix-based dereverberation for automatic speech recognition

Schwarz A, Reindl K, Kellermann W (2012)

Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2012

Publisher: VDE

Pages Range: 1-4

Article Number: 6309427

Event location: Aachen DE

ISBN: 9783800734511

URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84957707201∨igin=inward

Abstract

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.

Authors with CRIS profile

Andreas Schwarz Professur für Signalverarbeitung Klaus Reindl Professur für Signalverarbeitung Walter Kellermann Professur für Signalverarbeitung

How to cite

APA:

Schwarz, A., Reindl, K., & Kellermann, W. (2012). On blocking matrix-based dereverberation for automatic speech recognition. In Proceedings of the International Workshop on Acoustic Signal Enhancement (IWAENC) (pp. 1-4). Aachen, DE: VDE.

MLA:

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 VDE, 2012. 1-4.

BibTeX: Download