The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 22 of 283
Back to Result List

The REVERB Challenge: A Benchmark Task for Reverberation-Robust ASR Techniques

  • 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.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Keisuke Kinoshita, Marc DelcroixORCiD, Sharon GannotORCiD, Emanuël A. P. HabetsORCiD, Reinhold Haeb-UmbachORCiD, Walter Kellermann, Volker Leutnant, Roland Maas, Tomohiro NakataniORCiD, Bhiksha RajORCiD, Armin Sehr, Takuya Yoshioka
DOI:https://doi.org/10.1007/978-3-319-64680-0_15
ISBN:978-3-319-64679-4
Parent Title (English):New Era for Robust Speech Recognition
Publisher:Springer
Place of publication:Cham
Editor:Shinji Watanabe, Marc Delcroix, Florian Metze, John R. Hershey
Document Type:Part of a Book
Language:English
Year of first Publication:2017
Release Date:2022/06/05
Volume:27
First Page:345
Last Page:354
Institutes:Fakultät Elektro- und Informationstechnik
Fakultät Elektro- und Informationstechnik / Labor Elektroakustik
research focus:Information und Kommunikation
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG