[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[AUDITORY] REVERB Challenge (Call for Participation)

Dear list,

We are pleased to announce the launch of the REVERB Challenge
for speech enhancement and/or recognition in reverberant

Below is a brief description about the challenge.
We hope you will find the challenge interesting and consider

Best regards,

Tomohiro Nakatani
on behalf of the REVERB challenge organizers


       REVERB Challenge (Call for Participation)

      Result submission deadline: December 1, 2013
      Workshop: May 10, 2014, Florence, Italy


Recently, substantial progress has been made in the field of
reverberant speech signal processing, including both single-
and multi-channel de-reverberation techniques, and automatic
speech recognition (ASR) techniques robust to reverberation.
To evaluate state-of-the-art algorithms and draw new insights
regarding potential future research directions,
we call for participation in the REVERB (REverberant Voice
Enhancement and Recognition Benchmark) challenge that will
provide an opportunity to the researchers in the field
to carry out a comprehensive evaluation of their methods
based on a common database and on common evaluation metrics.
The challenge aims at bringing together researchers
from a broad range of disciplines to discuss novel and
established approaches to handle reverberant speech.
All entrants will be invited to submit papers describing their
work to a dedicated workshop held in conjunction with ICASSP2014
and HSCMA 2014.
This challenge is part of the IEEE SPS AASP challenge series.


You will find all information needed to get started on
the challenge webpage
( http://reverb2014.dereverberation.com/ )
Participants are required to evaluate their methods based on
the following data and task(s), and submit the evaluation results
and a paper that includes detailed description of their methods.

 - Task 1: Enhancement of reverberant speech
           with single-/multi-channel enhancement techniques
          (Evaluation metrics: objective and subjective measures)
 - Task 2: Robust recognition of reverberant speech
           (Evaluation metric: word error rate)
 - Data: Real and simulated 1-, 2-, and 8-channel recordings
         in reverberant meeting rooms based on the Wall Street
         Journal Corpus.
         This data is common for the following 2 tasks.

 - Details: http://reverb2014.dereverberation.com/

   *Participants are invited to take part in either or both of
    the above tasks.


The results will be presented by the participants
at the REVERB challenge workshop, which will be held
in conjunction with ICASSP2014 (http://icassp2014.org/)
and HSCMA2014 (http://hscma2014.inria.fr/).


Jul  1, 2013   Release of development data and evaluation tools
Nov  5, 2013   Release of evaluation data
Dec  1, 2013   Deadline for submission of results
Jan 10, 2014   Deadline for submission of papers
Feb 28, 2014   Notification of acceptance
May 10 2014    Workshop in conjunction with ICASSP2014
               and HSCMA2014


- Keisuke Kinoshita, Marc Delcroix, Takuya Yoshioka,
  Tomohiro Nakatani,
- Emanuel Habets,
  (Int. Audio Labs Erlangen)
- Reinhold Haeb-Umbach, Volker Leutnant,
  (Paderborn Univ.)
- Armin Sehr,
  (Beuth Univ. of Applied Sciences Berlin)
- Walter Kellermann, Roland Maas,
  (Univ. of Erlangen-Nuremberg)
- Sharon Gannot,
  (Bar-Ilan Univ.)
- Bhiksha Raj,
  (Carnegie Mellon Univ.)