The REVERB challenge: A benchmark task for reverberation-robust ASR techniques

Kinoshita K, Delcroix M, Gannot S, Habets E, Haeb-Umbach R, Kellermann W, Leutnant V, Maas R, Nakatani T, Raj B, Sehr A, Yoshioka T (2017)


Publication Language: English

Publication Type: Book chapter / Article in edited volumes

Publication year: 2017

Publisher: Springer International Publishing AG 2017

Edited Volumes: New Era for Robust Speech Recognition

Series: Exploiting Deep Learning

Pages Range: 345 - 354

ISBN: 978-3-319-64680-0

URI: https://link.springer.com/chapter/10.1007/978-3-319-64680-0_15#citeas

DOI: 10.1007/978-3-319-64680-0_15

Abstract

The REVERB challenge is a benchmark task designed to evaluate reverberation-robust  automatic speech recognition techniques under various conditions. A particular novelty of the REVERB challenge database is that it comprises both real reverberant speech recordings and simulated reverberant speech, both of which include tasks to evaluate techniques for 1-, 2-, and 8-microphone situations. In this chapter, we describe the problem of reverberation and  characteristics of the REVERB challenge data, and finally briefly introduce some results and findings useful for reverberant speech processing in the current deep-neural-network era.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Kinoshita, K., Delcroix, M., Gannot, S., Habets, E., Haeb-Umbach, R., Kellermann, W.,... Yoshioka, T. (2017). The REVERB challenge: A benchmark task for reverberation-robust ASR techniques. In Shinji Watanabe, Marc Delcroix, Florian Metze, John R. Hershey (Eds.), New Era for Robust Speech Recognition. (pp. 345 - 354). Springer International Publishing AG 2017.

MLA:

Kinoshita, Keisuke, et al. "The REVERB challenge: A benchmark task for reverberation-robust ASR techniques." New Era for Robust Speech Recognition. Ed. Shinji Watanabe, Marc Delcroix, Florian Metze, John R. Hershey, Springer International Publishing AG 2017, 2017. 345 - 354.

BibTeX: Download