Publication detail

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

KOCOUR, M. VESELÝ, K. SZŐKE, I. KESIRAJU, S. ZULUAGA-GOMEZ, J. BLATT, A. PRASAD, A. NIGMATULINA, I. MOTLÍČEK, P. KLAKOW, D. TART, A. KOLČÁREK, P. ČERNOCKÝ, J. CEVENINI, C. CHOUKRI, K. RIGAULT, M. LANDIS, F. SARFJOO, S.

Original Title

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

Type

conference paper

Language

English

Original 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-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.

Keywords

automatic speech recognition; air traffic control; contextual adaptation; language identification; named entity recognition; opensky network

Authors

KOCOUR, M.; VESELÝ, K.; SZŐKE, I.; KESIRAJU, S.; ZULUAGA-GOMEZ, J.; BLATT, A.; PRASAD, A.; NIGMATULINA, I.; MOTLÍČEK, P.; KLAKOW, D.; TART, A.; KOLČÁREK, P.; ČERNOCKÝ, J.; CEVENINI, C.; CHOUKRI, K.; RIGAULT, M.; LANDIS, F.; SARFJOO, S.

Released

18. 11. 2021

Publisher

MDPI

Location

Brussels

ISBN

2504-3900

Periodical

Proceedings

Year of study

2021

Number

12

State

Swiss Confederation

Pages from

1

Pages to

10

Pages count

10

URL

https://www.mdpi.com/2673-4591/13/1/8/htm

BibTex

@inproceedings{BUT176487,
  author="KOCOUR, M. and VESELÝ, K. and SZŐKE, I. and KESIRAJU, S. and ZULUAGA-GOMEZ, J. and BLATT, A. and PRASAD, A. and NIGMATULINA, I. and MOTLÍČEK, P. and KLAKOW, D. and TART, A. and KOLČÁREK, P. and ČERNOCKÝ, J. and CEVENINI, C. and CHOUKRI, K. and RIGAULT, M. and LANDIS, F. and SARFJOO, S.",
  title="Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data",
  booktitle="Proceedings of 9th OpenSky Symposium 2021, OpenSky Network, Brussels, Belgium",
  year="2021",
  journal="Proceedings",
  volume="2021",
  number="12",
  pages="1--10",
  publisher="MDPI",
  address="Brussels",
  doi="10.3390/engproc2021013008",
  issn="2504-3900",
  url="https://www.mdpi.com/2673-4591/13/1/8/htm"
}