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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU144937" target="_blank" >RIV/00216305:26230/22:PU144937 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9746301" target="_blank" >https://ieeexplore.ieee.org/document/9746301</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP43922.2022.9746301" target="_blank" >10.1109/ICASSP43922.2022.9746301</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ISBN

978-1-6654-0540-9

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

8357-8361

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Singapore

Místo konání akce

Singapore

Datum konání akce

22. 5. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000864187908133