- SJU reference # PJ.10-W2-96 ASR /Release 10
- Status In the pipeline
SPEECH-TO-TEXT TOOLS EASE CONTROLLER WORKLOAD
This Solution was formerly part of PJ.16-04
As in the previous candidate solution, controllers rely on their workstation to provide the support tools to manage air traffic and minimise workload in dense or complex airspace. Voice communications are central to controller activity yet risk being misheard or subject to congestion, prompting research into automatic speech recognition (ASR).
ASR takes audio signals and transforms them into text, for example for visualisation on the controller’s display. This candidate solution covers three aspects[TK1] of ASR with the aim of reducing workload and improving flight efficiency. The technology integrates artificial intelligence (AI) and machine learning algorithms to consider text predictions based on surveillance data; creating ATM commands based on existing ATC concepts; and a combination of both to provide further applications for the controller working position (CWP).
In detail, the ASR solution can analyse controller pilot communications and check commands against manual inputs. ASR can also highlight the relevant radar label and reduce the need for manual inputs via mouse or keyboard. By predicting possible controller commands, it can check issued commands to ensure consistency, and can maintain a history of commands and readback for each aircraft. SESAR research is also examining how ASR may be used to enable faster and more predictable navigation in 3D visualisations of the airspace sectorisation when using dynamic airspace configuration (DAC).
Expanding on Wave 1 results, the candidate solution enhances safety and contributes to ASR standards development.
Improved flight efficiency