Description

The reverberation contained in speech signals captured by distant microphones reduces both the perceptual speech quality and the performance of automatic speech recognition (ASR) systems, hampering both human-human communication and human-machine interaction. Thus, for applications that depend on distant sound capture, processing of the speech signal to mitigate the reverberation problem is essential. Such applications include voice control of consumer products, e.g. smart phones, wearable devices, interactive TVs, and appliances in smart homes; hearing aids; voice communication with robots and avatars; automatic meeting transcription; speech recognition in call centers; automatic annotation of videos; speech-to-speech translation.

To enable researchers in the field of reverberant speech processing to carry out comprehensive evaluations of their methods based on a common database and common evaluation metrics, recently the Reverberant Voice Enhancement and Recognition Benchmark (REVERB) challenge has been organized. Inspired by the great interest induced by this challenge, we invite contributions on processing of reverberant speech signals both for signal enhancement to increase perceptual speech quality and for robust recognition of reverberant speech.

We strongly encourage the evaluation of the proposed approaches on the data provided by the REVERB challenge. Alternatively or additionally, well-documented and publicly available, databases can be used. We invite challenge participants to submit extended descriptions of their (enhanced) systems. Participation in the challenge is however not a prerequisite for submitting a contribution to this special issue.

Topics of interest include:

• Single-channel and multichannel speech dereverberation algorithms
• ASR robust to reverberation
• Interconnection of dereverberation and ASR systems
• Objective measures for evaluating the perceptual speech quality of dereverberated signals
• Estimation of reverberation parameters (e.g. reverberation time, direct-to-reverberation ratio)
• Dereverberation in dynamic scenarios
• Highly reverberant scenarios (reverberation times exceeding one second, e.g., concert halls, museums, terminal halls, houses of worship)
• System design for handling reverberant speech

Guest Editors

• Sharon Gannot, Faculty of Engineering, Bar-Ilan University, Israel
• Armin Sehr, Beuth Hochschule für Technik Berlin
• Emanuël Habets, Friedrich-Alexander-University of Erlangen-Nuremberg
• Keisuke Kinoshita, NTT Communication Science Laboratories
• Walter Kellermann, University Erlangen-Nuernberg, Germany
• Reinhold Haeb-Umbach, Department of Communications Engineering, University of Paderborn, Germany