2nd Spoken CALL Shared Task

27 Oct 2017, Training data and resources released
Below you can find the announcement.

Some URLs:

Announcement – 2nd edition of the ‘Spoken CALL Shared Task’

Dear colleagues,

Recently, we organized the first ‘Spoken CALL Shared Task’ [https://regulus.unige.ch/spokencallsharedtask/].
Results were presented at a special session of the SLaTE-2017 workshop [http://www.slate2017.org/].

The first ‘Spoken CALL Shared Task’ was successful, people expressed interest in a follow-up, and that is why we are now organizing a 2nd edition of the ‘Spoken CALL Shared Task’ [http://tiny.cc/2nd-spoken-CALL-task ~ https://regulus.unige.ch/spokencallsharedtask_2ndedition/].
The second version of the task will offer improved resources. In particular, it will make available the highest-performing speech recognizer from the first version of the task, and about twice as much training data.

The preliminary schedule of the 2nd ‘Spoken CALL Shared Task’ is as follows:

  • 27 Oct 2017, Training data and resources released
  • 31 Jan 2018, Release test data
  • 7 Feb 2018, Deadline for submission of entries
  • 23 Mar 2018, Interspeech submission deadline
  • 2-6 Sep 2018, Presentations at a special session of Interspeech-2018

If you are interested (even if you are not sure that you will [be able to] participate),
Subscribe to the Newsletter at https://regulus.unige.ch/spokencallsharedtask_2ndedition/,
and/or send an email to Johanna.Gerlach@unige.ch
There are no obligations at all, this is just to have an initial idea about who is interested.

Feel free to forward this announcement.
If you have suggestions about where we can send this announcement, please let us know.

Regards,
The ‘Spoken CALL Shared Task’ team

ISCA SIG SLaTE: Speech and Language Technology in Education