Publication Details

A Two-Step Approach to Leverage Contextual Data: Speech Recognition in Air-Traffic Communications

NIGMATULINA, I.; ZULUAGA-GOMEZ, J.; PRASAD, A.; SARFJOO, S.; MOTLÍČEK, P. A Two-Step Approach to Leverage Contextual Data: Speech Recognition in Air-Traffic Communications. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Singapore: IEEE Signal Processing Society, 2022. p. 6282-6286. ISBN: 978-1-6654-0540-9.
Czech title
Dvoustupňový přístup pro využité kontextuálních dat: rozpoznávání řeči v letectví
Type
conference paper
Language
English
Authors
NIGMATULINA, I.
ZULUAGA-GOMEZ, J.
Prasad Amrutha (DCGM)
SARFJOO, S.
Motlíček Petr, doc. Ing., Ph.D. (DCGM)
URL
Keywords

automatic speech recognition, human-computer interaction, Air-Traffic Control, Air-Surveillance Data, Callsign Detection, finite-state transducers

Abstract

Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR application can lead to a lower number of incidents caused by misunderstanding and improve air traffic management (ATM) efficiency. Evidently, high accuracy predictions, especially, of key information, i.e., callsigns and commands, are required to minimize the risk of errors. We prove that combining the benefits of ASR and Natural Language Processing (NLP) methods to make use of surveillance data (i.e. additional modality) helps to considerably improve the recognition of callsigns (named entity). In this paper, we investigate a two-step callsign boosting approach: (1) at the 1st step (ASR), weights of probable callsign n-grams are reduced in G.fst and/or in the decoding FST (lattices), (2) at the 2nd step (NLP), callsigns extracted from the improved recognition outputs with Named Entity Recognition (NER) are correlated with the surveillance data to select the most suitable one. Boosting callsign n-grams with the combination of ASR and NLP methods eventually leads up to 53.7% of an absolute, or 60.4% of a relative, improvement in callsign recognition.

Published
2022
Pages
6282–6286
Proceedings
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISBN
978-1-6654-0540-9
Publisher
IEEE Signal Processing Society
Place
Singapore
DOI
10.1109/ICASSP43922.2022.9746563
UT WoS
000864187906114
EID Scopus
2-s2.0-85128558160
BibTeX 
@inproceedings{BUT178411,
  author="NIGMATULINA, I. and ZULUAGA-GOMEZ, J. and PRASAD, A. and SARFJOO, S. and MOTLÍČEK, P.",
  title="A Two-Step Approach to Leverage Contextual Data: Speech Recognition in Air-Traffic Communications",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2022",
  pages="6282--6286",
  publisher="IEEE Signal Processing Society",
  address="Singapore",
  doi="10.1109/ICASSP43922.2022.9746563",
  isbn="978-1-6654-0540-9",
  url="https://ieeexplore.ieee.org/document/9746563"
}
Back to top