AIRBUS, in collaboration with IRIT and SAFETY DATA-CFH, is launching a challenge on automatic speech recognition of English Air Traffic Control (ATC) communications to:

- identify top players in the field for future collaboration;
- encourage research community to tackle the specific issues of ATC (accent / noise / code-switching robustness, highly specific vocabulary).

Why is it challenging?
ATC audio is very noisy, made of non-native speech, with code switching, high speech rate and lots of domain-specific vocabulary -- see here for example.

What are the tasks?
- Standard audio transcription (evaluated with WER)
- Call sign extraction (evaluation with Precison/Recall/F1)

What is the dataset?
40h of transcribed real-life non-native English ATC data
+ 5h for validation/leader board
+ 5h for final evaluation
you can use your own additional data

What is there to win?
- #1 will be invited to speak at the challenge workshop and to visit Airbus facility and simulators.
- 5 of the best challengers will be retained for a second internal selection aiming to choose Airbus R&T partner for developing future on-board speech-to-text solutions.

Who can participate?
Anyone: start-ups, medium & big companies, research labs.
You can participate in the challenge even if you are not considering a partnership with AIRBUS or if you are planning to do only one of the tasks.

Important dates
Declaration of intent: Now, write to
Registration open: Mon 5th February, via AIRBUS challenge platform
Training data available + leader board:  Mon 5th March - Sun 29th April (8 weeks)
Release of evaluation data: Wed 2nd May
Results submission: Wed 9th May
Final workshop: between Mon 18th and Fri 22nd June (date to be confirmed)
Special session at international conference for publication: pending approval (submitted)

More questions?
Post to the challenge forum or write to