Publication Details

Lessons Learned in Transcribing 5000 h of Air Traffic Control Communications for Robust Automatic Speech Understanding

ZULUAGA-GOMEZ Juan, NIGMATULINA Iuliia, PRASAD Amrutha, MOTLÍČEK Petr, KHALIL Driss, MADIKERI Srikanth, TART Allan, SZŐKE Igor, LENDERS Vincent, RIGAULT Mickael and CHOUKRI Khalid. Lessons Learned in Transcribing 5000 h of Air Traffic Control Communications for Robust Automatic Speech Understanding. Aerospace, vol. 2023, no. 10, pp. 1-33. ISSN 2226-4310. Available from: https://www.mdpi.com/2226-4310/10/10/898
Czech title
Poznatky získané při přepisu 5000 hodin komunikace řízení letového provozu pro robustní automatické porozumění řeči
Type
journal article
Language
english
Authors
Zuluaga-Gomez Juan (IDIAP)
Nigmatulina Iuliia (IDIAP)
Prasad Amrutha (DCGM FIT BUT)
Motlíček Petr, doc. Ing., Ph.D. (DCGM FIT BUT)
Khalil Driss (IDIAP)
Madikeri Srikanth (IDIAP)
Tart Allan (OpenSky)
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Lenders Vincent ()
Rigault Mickael (ELRA)
Choukri Khalid (ELRA)
URL
Keywords

air traffic control communications; automatic speech recognition and understanding; OpenSky Network; callsign recognition; ADS-B data

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.

Published
2023
Pages
1-33
Journal
Aerospace, vol. 2023, no. 10, ISSN 2226-4310
Publisher
MDPI
DOI
10.3390/aerospace10100898
UT WoS
001093774900001
EID Scopus
2-s2.0-85175267376
BibTeX 
@ARTICLE{FITPUB13113,
   author = "Juan Zuluaga-Gomez and Iuliia Nigmatulina and Amrutha Prasad and Petr Motl\'{i}\v{c}ek and Driss Khalil and Srikanth Madikeri and Allan Tart and Igor Sz\H{o}ke and Vincent Lenders and Mickael Rigault and Khalid Choukri",
   title = "Lessons Learned in Transcribing 5000 h of Air Traffic Control Communications for Robust Automatic Speech Understanding",
   pages = "1--33",
   journal = "Aerospace",
   volume = 2023,
   number = 10,
   year = 2023,
   ISSN = "2226-4310",
   doi = "10.3390/aerospace10100898",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/13113"
}
Back to top