%Aigaion2 BibTeX export from Idiap Publications
%Sunday 25 February 2024 12:30:32 AM

         author = {Juan, Zuluaga-Gomez. and Iuliia, Nigmatulina and Prasad, Amrutha and Motlicek, Petr and Khalil, Driss and Madikeri, Srikanth and Tart, Allan and Szoke, Igor and Lenders, Vincent and Rigault, Mickael and Choukri, Khalid},
       keywords = {ADS-B data, air traffic control communications, automatic speech recognition and understanding, Call-sign Recognition, OpenSky Network},
          month = oct,
          title = {Lessons Learned in Transcribing 5000 h of Air Traffic Control Communications for Robust Automatic Speech Understanding},
        journal = {Aerospace},
         volume = {10},
         number = {10},
           year = {2023},
            url = {https://www.mdpi.com/2226-4310/10/10/898},
            doi = {https://doi.org/10.3390/aerospace10100898},
       abstract = {Voice communication between air traffic controllers (ATCos) and pilots is critical for ensuring safe and efficient air traffic control (ATC). The handling of these voice communications requires high levels of awareness from ATCos and can be tedious and error-prone. Recent attempts aim at integrating artificial intelligence (AI) into ATC communications in order to lessen ATCos’s workload. However, the development of data-driven AI systems for understanding of spoken ATC communications demands large-scale annotated datasets, which are currently lacking in the field. This paper explores the lessons learned from the ATCO2 project, which aimed to develop an unique platform to collect, preprocess, and transcribe large amounts of ATC audio data from airspace in real time. This paper reviews (i) robust automatic speech recognition (ASR), (ii) natural language processing, (iii) English language identification, and (iv) contextual ASR biasing with surveillance data. The pipeline developed during the ATCO2 project, along with the open-sourcing of its data, encourages research in the ATC field, while the full corpus can be purchased through ELDA. ATCO2 corpora is suitable for developing ASR systems when little or near to no ATC audio transcribed data are available. For instance, the proposed ASR system trained with ATCO2 reaches as low as 17.9\% WER on public ATC datasets which is 6.6\% absolute WER better than with “out-of-domain” but gold transcriptions. Finally, the release of 5000 h of ASR transcribed speech—covering more than 10 airports worldwide—is a step forward towards more robust automatic speech understanding systems for ATC communications.},
            pdf = {https://publications.idiap.ch/attachments/papers/2023/Juan_AEROSPACE_2023.pdf}