Part of the EU Network of Excellence PASCAL Challenge Program with support from EPSRC project CHiME. Participation is open to all.
The object of the challenge is to separate and recognise spoken command utterances appearing in background recordings made in a noisy domestic living room using binaural microphones. The challenge is motivated by the demands of real distant-microphone speech recognition applications and in particular the need to deal with multiple and highly varied interfering sound sources. The challenge has been designed to draw participation from multiple disciplines including signal processing, computational hearing, machine learning and speech recognition. Evaluation will be through speech recognition results but participants will be allowed to submit either separated signals, robust speech features or the outputs of complete recognition systems. We are interested in measuring the performance of both emerging techniques and established approaches.
A full description of the challenge, including details of the source separation and recognition tasks, the noisy speech data sets, and the rules for participation can be found on the PASCAL CHiME Challenge web site.
Results of the Challenge will be presented at a dedicated one-day workshop, “Machine Listening in Multisource Environments” to be held as a satellite event of Interspeech 2011 in Florence, Italy. Participants will be invited to submit abstracts or full papers for presentation at this event.
A Special Issue of the journal Computer Speech and Language on the theme of Speech Separation and Recognition in Multisource Environments will be published as an outlet for extended workshop papers.
Now: Data and evaluation tools are available for download
30 March: Final test data are released
14th April: Submission deadline for Challenge workshop abstracts/papers.
21st April: Submission deadline for Challenge results.
1st September: CHiME Workshop, Florence, Italy
Jon Barker, University of Sheffield, UK
Emmanuel Vincent, INRIA Rennes, France
Phil Green, University of Sheffield, UK
Heidi Christensen, University of Sheffield, UK
Ning Ma, University of Sheffield, UK