Incorrect Read-back Detection in Air Traffic Control

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21260%2F24%3A00379810" target="_blank" >RIV/68407700:21260/24:00379810 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S2352146524002783" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2352146524002783</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.trpro.2024.11.027" target="_blank" >10.1016/j.trpro.2024.11.027</a>

Result language

angličtina

Original language name

Incorrect Read-back Detection in Air Traffic Control

Original language description

Read-back is a procedure in which a receiving station (flight crew) repeats the received message, or a specific part of it, back to the broadcasting station (Air Traffic Controller) to ensure that the message was received correctly. Incorrect read-back may lead to deviation from the intended clearance issued by the Air Traffic Controller and may only be discovered once the deviation is visible on the radar screen of the Air Traffic Controller. The presented research aims to find methods to design and develop a software tool that would identify wrong read-back in standard phraseology and, notify the Air Traffic Controller. Subsequently, the Automatic Speech Recognition (ASR) software's success rate and test subjects' capability to identify wrong read-back in an experiment is being tested. Results showed that the first iteration of the ASR system, which has not been modified to the specifics of aviation phraseology, reached a success rate of wrong read-back evaluation of 69,9 %. The lowest success rate was recorded for long and complex route clearances. On the other hand, the incorrect read-back detection by the 50 tested subjects reached 95,6 %. The experiment results show that even with limited financial resources, a reasonable transcription success rate can be achieved, given the rapid advances in computing technology and the development of artificial intelligence. Therefore, in terms of detecting wrong read-back, is Automatic Speech Recognition technology is very promising and can significantly improve air traffic safety in the future.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

20202 - Communication engineering and systems

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2024

Confidentiality

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

Article name in the collection

Transportation Research Procedia

ISBN

—

ISSN

2352-1465

e-ISSN

2352-1465

Number of pages

10

Pages from-to

256-265

Publisher name

Elsevier B.V.

Place of publication

Amsterdam

Event location

Bratislava

Event date

Oct 23, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—