Nowadays, instructions from air traffic control (ATC) to pilots are usually given via voice communication, but controllers need to manually type all the information into the electronic flight strip systems. Recent years has seen significant progress made with machine learning applications that improve the performance of automatic speech recognition (ASR), making it possible to convert spoken words into digital machine-readable formats with the reliability required in the safety critical ATC domain.
This new technology offers the means to avoid the manual input of given ATC commands and enables safety improvements like automatic read-back error detection support and automatic call sign detection.
Within SESAR 2020, several projects are researching and developing ASR technologies to see what they can bring to the ATC working environment. This webinar gave the state-of-play of SESAR JU research and development, and in particular:
- Provided an overview of why voice recognition has taken so long to arrive to ATC;
- Showcased some of the more advanced ASR applications being researched under the SESAR 2020 Exploratory Research programme.
- Gave the audience a chance to hear experiences of ANSPs working on the applications within the SESAR programme;
Agenda:
Welcome and Introduction
Olivia Nunez, ATM Expert, SESAR Joint Undertaking
The need for research on ASR in ATM
Hon. Prof. Dr. Hartmut Helmke, HAAWAII project lead, DLR
Illuminating flights using speech recognition
Raquel Garcia Lasheras, R&D Engineer, CRIDA
Application of ASR in the tower environment
Ramona Santarelli, Engineer, ENAV
The view of an Air Navigation Service Provider: The costs and benefits of ASR for Austro Control
Christian Kern, Director of Operations, Austro Control
Christian Windisch, Senior Air Traffic Management Expert, Austro Control
Questions and Answers
Moderated by Olivia Nunez, ATM Expert, SESAR Joint Undertaking