Coherence-based dereverberation for automatic speech recognition

Schwarz A, Brendel A, Kellermann W (2014)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2014

City/Town: Oldenburg, Germany

Pages Range: 525-526

Event location: Oldenburg DE

Abstract

The idea of performing dereverberation using a short-time spatial coherence estimate dates back to 1977 [1], when it was proposed to essentially use the magnitude of the coherence as gain for reverberation suppression. Another heuristic method was recently proposed in [2], where a soft threshold function is used to compute a gain from the coherence magnitude, and the parameters of the threshold function are adapted depending on the histogram of the coherence magnitude in each frequency bin. Short-time coherence estimates have also been investigated in the context of beamforming as a so-called postfilter, and solutions for supression of uncorrelated and diffuse noise have been proposed [3]. In this contribution, we focus on methods where, first, the ratio between direct and reverberation signal components (coherent-to-diffuse ratio, CDR) is estimated from a short-time coherence estimate, and filter weights for reverberation suppression are computed from the CDR using, e.g., the Wiener filter or spectral subtraction rule. We compare and illustrate the behavior of a number of different CDR estimators that have been proposed over the past years, and propose a new variant. Finally, we compare the practical effect of the methods by processing reverberated speech and evaluating the recognition accuracy achieved by an automatic speech recognizer with the processed signals.

Authors with CRIS profile

How to cite

APA:

Schwarz, A., Brendel, A., & Kellermann, W. (2014). Coherence-based dereverberation for automatic speech recognition. In Proceedings of the Deutsche Jahrestagung für Akustik (DAGA) (pp. 525-526). Oldenburg, DE: Oldenburg, Germany.

MLA:

Schwarz, Andreas, Andreas Brendel, and Walter Kellermann. "Coherence-based dereverberation for automatic speech recognition." Proceedings of the Deutsche Jahrestagung für Akustik (DAGA), Oldenburg Oldenburg, Germany, 2014. 525-526.

BibTeX: Download