A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

By Keisuke Kinoshita, Marc Delcroix, Sharon Gannot, Emanuël Habets, Reinhold Häb-Umbach, Walter Kellermann, Volker Leutnant, Roland Maas, Tomohiro Nakatani, Bhiksha Raj and 2 more. EURASIP Journal on Advances in Signal Processing, 2016

398 citations recorded by the source corpus.

In recent years, substantial progress has been made in the field of reverberant speech signal processing, including both single- and multichannel dereverberation techniques and automatic speech recognition (ASR) techniques that are robust to reverberation. In this paper, we describe the REVERB challenge, which is an evaluation campaign that was designed to evaluate such speech enhancement (SE) and ASR techniques to reveal the state-of-the-art techniques and obtain new insights regarding potential future research directions. Even though most existing benchmark tasks and challenges for distant speech processing focus on the noise robustness issue and sometimes only on a single-channel scenario, a particular novelty of the REVERB challenge is that it is carefully designed to test robustness against reverberation, based on both real, single-channel, and multichannel recordings. This challenge attracted 27 papers, which represent 25 systems specifically designed for SE purposes and 49 systems specifically designed for ASR purposes. This paper describes the problems dealt within the challenge, provides an overview of the submitted systems, and scrutinizes them to clarify what current processing strategies appear effective in reverberant speech processing.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e5d7e9dd7bab656b747df74b40dc8728700791b5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition (2018, background): “Recently, due to their strong regression learning abilities, deep neutral networks (DNNs) have been used in speech enhancement [12] and later in speech dereverberation [3, 4].”
Front-end processing for the CHiME-5 dinner party scenario (2018, background): “Many of these developments have been spurred by recent challenges like REVERB [3], CHiME-3 [4] and CHiME-4 [5], which showcased the benefits of a strong speech enhancement front-end for Automatic Speech Recognition (ASR).”
Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement (2020, methodology): “…of the clean speeches are mixed with randomly selected room impulse responses (RIR) from (1) the Multichannel Impulse Response Database [20] with three reverberation times (T60) 0.16 s, 0.36 s, and 0.61 s. (2) the Reverb Challenge dataset [21] with three reverberation times 0.3 s, 0.6 s and 0.7 s.”
Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis (2022, background): “Although the objective metrics shown in Table 2 speech quality [27].”
Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, methodology): “2016 [11] it was found that many systems significantly decreased the amount of reverberation perceived by listeners but only one system [12] improved subjective quality when com-”
Attentive Statistics Pooling for Deep Speaker Embedding (2018, methodology): “We also applied data augmentation to the training set in the following ways: (a) Additive noise: each segment was mixed with one of the noise samples in the PRISM corpus [20] (SNR: 8, 15, or 20dB), (b) Reverberation: each segment was convolved with one of the room impulse responses in the REVERB cha”
Speech Dereverberation Using Fully Convolutional Networks (2018, methodology): “The REVERB challenge [3] was a large community-wide endeavor to put together a common dataset for testing dereverberation algorithms and for evaluating many algorithms on a common ground.”
Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge (2018, background): “Related public evaluation campaigns also include SiSEC challenge on signal separation [4] and the REVERB challenge on reverberant speech processing research [5].”
Deep Learning for Environmentally Robust Speech Recognition (2017, neutral): “Microphone arrays and multi-channel processing techniques have recently played an increasingly significant role in the development of robust ASR [8], [9].”