Machine Learning of Speech Recognition Models for Controller Assistance
MALORCA project (http://www.malorca-project.de) offers machine learning framework as a general, cheap and effective solution to automate the adaptation and customization process of ATM decision support tools. Adaptation of speech recognition models were selected as a first show-case of the project. The proposed solution builds on the huge amount of target data recorded every day in the operation rooms. Each ANSP generates large amount of radar data and voice recordings on a daily basis. These recordings are the input for machine learning algorithms, which improve the models of a basic ABSR system. Improvement is possible once or permanently on daily basis. If a new waypoint is added it would be learned, if a waypoint is removed it would be “unlearned” etc.
The Horizon 2020 SESAR project MALORCA (Machine Learning of Speech Recognition Models for Controller Assistance) is partly funded by SESAR Joint Undertaking (Grant Number 698824). MALORCA proposes a general, cheap and effective solution to automate this re-learning, adaptation and customisation process by automatically learning local speech recognition and controllers models from radar and speech data recordings
The German Aerospace Center (DLR), Saarland University (USAAR), Idiap Research Institute (Idiap), Austro Control Österreichische Gesellschaft für Zivilluftfahrt mit beschränkter Haftung (ACG), and Air Navigation Services of the Czech Republic (ANS CR) work together to automatically and more efficiently improve speech recognition models for assistance at different controller working positions.
