Publication Details

Call-Sign Recognition and Understanding for Noisy Air-Traffic Transcripts Using Surveillance Information

BLATT Alexander, KOCOUR Martin, VESELÝ Karel, SZŐKE Igor and KLAKOW Dietrich. Call-Sign Recognition and Understanding for Noisy Air-Traffic Transcripts Using Surveillance Information. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Singapore: IEEE Signal Processing Society, 2022, pp. 8357-8361. ISBN 978-1-6654-0540-9. Available from: https://ieeexplore.ieee.org/document/9746301
Czech title
Rozpoznávání a porozumění volacím znakům pro přepis řeči v letectví s využitím radarových informací
Type
conference paper
Language
english
Authors
Blatt Alexander (UDS)
Kocour Martin, Ing. (DCGM FIT BUT)
Veselý Karel, Ing., Ph.D. (DCGM FIT BUT)
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Klakow Dietrich (UDS)
URL
Keywords

Air Traffic Control, Call-sign Recognition, Context Incorporation, Data Augmentation

Abstract

Air traffic control (ATC) relies on communication via speech between pilot and air-traffic controller (ATCO). The call-sign, as unique identifier for each flight, is used to address a specific pilot by the ATCO. Extracting the call-sign from the communication is a challenge because of the noisy ATC voice channel and the additional noise introduced by the receiver. A low signal-to-noise ratio (SNR) in the speech leads to high word error rate (WER) transcripts. We propose a new call-sign recognition and understanding (CRU) system that addresses this issue. The recognizer is trained to identify call-signs in noisy ATC transcripts and convert them into the standard International Civil Aviation Organization (ICAO) format. By incorporating surveillance information, we can multiply the call-sign accuracy (CSA) up to a factor of four. The introduced data augmentation adds additional performance on high WER transcripts and allows the adaptation of the model to unseen airspaces.

Published
2022
Pages
8357-8361
Proceedings
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Conference
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), Singapore, SG
ISBN
978-1-6654-0540-9
Publisher
IEEE Signal Processing Society
Place
Singapore, SG
DOI
UT WoS
000864187908133
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12789,
   author = "Alexander Blatt and Martin Kocour and Karel Vesel\'{y} and Igor Sz\H{o}ke and Dietrich Klakow",
   title = "Call-Sign Recognition and Understanding for Noisy Air-Traffic Transcripts Using Surveillance Information",
   pages = "8357--8361",
   booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
   year = 2022,
   location = "Singapore, SG",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-6654-0540-9",
   doi = "10.1109/ICASSP43922.2022.9746301",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12789"
}
Back to top