Next Article in Journal
Optimal Analysis of 40 Gbps Dispersion Compensated Optical Fiber System
Previous Article in Journal
Cellulose Blended Membranes for High-Salinity Water Pervaporation Desalination
 
 
Search for Articles:
Title / Keyword
Author / Affiliation
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Engineering Proceedings
Volume 13
Issue 1
10.3390/engproc2021013008
engproc-logo
Submit to this Journal
► Article Menu

Article Menu

share announcement question_answer thumb_up
...
textsms
...
Proceeding Paper

Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data †

by
Martin Kocour
1,*,
Karel Veselý
1,*,
Igor Szöke
1,2,
Santosh Kesiraju
1,
Juan Zuluaga-Gomez
3,4,
Alexander Blatt
5,
Amrutha Prasad
3,
Iuliia Nigmatulina
3,
Petr Motlíček
3,
Dietrich Klakow
5,
Allan Tart
6,
Hicham Atassi
7,
Pavel Kolčárek
7,
Jan Černocký
1,
Claudia Cevenini
8,
Khalid Choukri
9,
Mickael Rigault
9,
Fabian Landis
6,
Saeed Sarfjoo
3 and
Chloe Salamin
3
1
[email protected], Faculty of Information Technology, Brno University of Technology, 61200 Brno, Czech Republic
2
ReplayWell, 61200 Brno, Czech Republic
3
Idiap Research Institute, 1920 Martigny, Switzerland
4
Ecole Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
5
Department of Language Science & Technology, Saarland Informatics Campus, Saarland University, 66123 Saarbrücken, Germany
6
OpenSky Network, 3400 Burgdorf, Switzerland
7
Honeywell, 62700 Brno, Czech Republic
8
Romagna Tech, 47121 Forli, Italy
9
Evaluations and Language Resources Distribution Agency (ELDA), 75013 Paris, France
*
Authors to whom correspondence should be addressed.
†
Presented at the 9th OpenSky Symposium, Brussels, Belgium, 18–19 November 2021.
Academic Editor: Junzi Sun
Eng. Proc. 2021, 13(1), 8; https://doi.org/10.3390/engproc2021013008
Published: 31 December 2021
(This article belongs to the Proceedings of The 9th OpenSky Symposium)
View Full-Text Download PDF
Browse Figures

Abstract

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-to-text’ (ASR) module, (f) English language detection, (g) call-sign code recognition, (h) ATCO—pilot 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 semi-supervised 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. View Full-Text
Keywords: automatic speech recognition; air traffic control; contextual adaptation; language identification; named entity recognition; opensky network automatic speech recognition; air traffic control; contextual adaptation; language identification; named entity recognition; opensky network
►▼ Show Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
SciFeed

Share and Cite

MDPI and ACS Style

Kocour, M.; Veselý, K.; Szöke, I.; Kesiraju, S.; Zuluaga-Gomez, J.; Blatt, A.; Prasad, A.; Nigmatulina, I.; Motlíček, P.; Klakow, D.; Tart, A.; Atassi, H.; Kolčárek, P.; Černocký, J.; Cevenini, C.; Choukri, K.; Rigault, M.; Landis, F.; Sarfjoo, S.; Salamin, C. Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data. Eng. Proc. 2021, 13, 8. https://doi.org/10.3390/engproc2021013008

AMA Style

Kocour M, Veselý K, Szöke I, Kesiraju S, Zuluaga-Gomez J, Blatt A, Prasad A, Nigmatulina I, Motlíček P, Klakow D, Tart A, Atassi H, Kolčárek P, Černocký J, Cevenini C, Choukri K, Rigault M, Landis F, Sarfjoo S, Salamin C. Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data. Engineering Proceedings. 2021; 13(1):8. https://doi.org/10.3390/engproc2021013008

Chicago/Turabian Style

Kocour, Martin, Karel Veselý, Igor Szöke, Santosh Kesiraju, Juan Zuluaga-Gomez, Alexander Blatt, Amrutha Prasad, Iuliia Nigmatulina, Petr Motlíček, Dietrich Klakow, Allan Tart, Hicham Atassi, Pavel Kolčárek, Jan Černocký, Claudia Cevenini, Khalid Choukri, Mickael Rigault, Fabian Landis, Saeed Sarfjoo, and Chloe Salamin. 2021. "Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data" Engineering Proceedings 13, no. 1: 8. https://doi.org/10.3390/engproc2021013008

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Metrics

Article Access Map by Country/Region

1
Back to TopTop