CHiME-3
Supported by IEEE ASRU 2015
The 3rd CHiME challenge is now complete. Final results were presented at a special session at the IEEE ASRU conference on 17th December 2015. Please visit the results page for a full overview of the performance of the 26 systems submitted.
Following the success of the 2011 and 2013 CHiME challenges it gives us great pleasure to pre-announce the 3rd CHiME Speech Separation and Recognition Challenge (CHiME-3). The new challenge is designed around the popular Wall Street Journal corpus and features talkers speaking in challenging noisy environments recorded using a 6-channel tablet based microphone array.
All approaches are welcome, whether they are emerging or established, and whether they rely on speech processing, signal separation or machine learning.
On this web site you will find everything you need to get started, including,
- a task overview providing details of the motivation and recording set up,
- a description of the training and development datasets,
- baseline enhancement, recognition and evaluation tools,
- a detailed description of the challenge rules,
- instructions on how to submit your results.
CHiME-3 is an official IEEE ASRU 2015 Challenge Task. Participants will be invited to submit CHiME-3 papers to the ASRU workshop to be held in Scottsdale, Arizona 13-17 December. All challenge participants will be given the opportunity to present their systems during an ASRU special CHiME Challenge session.
IMPORTANT DATES
- Mar 2, 2015 — Launch - Training data + dev data release
- June 3, 2015 — Test set released
- July 10, 2015 — Challenge paper submission deadline
- September 11, 2015 — Paper notification & release of CHiME-3 results
- December 13-17, 2015 — ASRU Workshop
ORGANISERS
- Jon Barker, University of Sheffield
- Ricard Marxer, University of Sheffield
- Emmanuel Vincent, Inria
- Shinji Watanabe, MERL
Sponsors