Publication Details
Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data
Veselý Karel, Ing., Ph.D. (DCGM FIT BUT)
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Kesiraju Santosh (DCGM FIT BUT)
Zuluaga-Gomez Juan (IDIAP)
Blatt Alexander (UDS)
Prasad Amrutha (IDIAP)
Nigmatulina Iuliia (IDIAP)
Motlíček Petr, Ing., Ph.D. (IDIAP)
Klakow Dietrich (UDS)
Tart Allan (OpenSky)
Kolčárek Pavel (Honeywell)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Cevenini Claudia (RomagnaTech)
Choukri Khalid (ELRA)
Rigault Mickael (ELRA)
Landis Fabian (OpenSky)
and others
automatic speech recognition; air traffic control; contextual adaptation; language identification; named entity recognition; opensky network
This document describes our pipeline for automatic processing of ATCO pilot audio communication we developed as part of the ATCO2 project. So far, we collected two thousand hours of audio recordings that we either preprocessed for the transcribers or used for semi-supervised training. Both methods of using the collected data can further improve our pipeline by retraining our models. The proposed automatic processing pipeline is a cascade of many standalone components: (a) segmentation, (b) volume control, (c) signal-to-noise ratio filtering, (d) diarization, (e) speech-totext (ASR) module, (f) English language detection, (g) call-sign code recognition, (h) ATCOpilot classification and (i) highlighting commands and values. The key component of the pipeline is a speech-to-text transcription system that has to be trained with real-world ATC data; otherwise, the performance is poor. In order to further improve speech-to-text performance, we apply both semisupervised training with our recordings and the contextual adaptation that uses a list of plausible callsigns from surveillance data as auxiliary information. Downstream NLP/NLU tasks are important from an application point of view. These application tasks need accurate models operating on top of the real speech-to-text output; thus, there is a need for more data too. Creating ATC data is the main aspiration of the ATCO2 project. At the end of the project, the data will be packaged and distributed by ELDA.
@INPROCEEDINGS{FITPUB12687,
author = "Martin Kocour and Karel Vesel\'{y} and Igor Sz\H{o}ke and Santosh Kesiraju and Juan Zuluaga-Gomez and Alexander Blatt and Amrutha Prasad and Iuliia Nigmatulina and Petr Motl\'{i}\v{c}ek and Dietrich Klakow and Allan Tart and Pavel Kol\v{c}\'{a}rek and Jan \v{C}ernock\'{y} and Claudia Cevenini and Khalid Choukri and Mickael Rigault and Fabian Landis and Saeed Sarfjoo and et al.",
title = "Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data",
pages = "1--10",
booktitle = "Proceedings of 9th OpenSky Symposium 2021, OpenSky Network, Brussels, Belgium",
journal = "Proceedings",
volume = 2021,
number = 12,
year = 2021,
location = "Brussels, BE",
publisher = "MDPI",
ISSN = "2504-3900",
doi = "10.3390/engproc2021013008",
language = "english",
url = "https://www.fit.vut.cz/research/publication/12687"
}