Doctoral student position at the School of Electrical Engineering and Computer Science at KTH Royal Institute of Technology.
The goal is to implement and evaluate the usefulness of a generative AI and expressive speech synthesis in Augmentative Communication Technology for individuals with communication disabilities. The project will use the KTH conversational text-to-speech system with context-adaptive expressive control (https://www.speech.kth.se/tts-demos/), As the AI voice system is designed for users who input text using gaze trackers the project also involves using Large Language models to speed up the text input given the previous context. The research takes place at the division of speech, music and hearing, in an interdisciplinary group focusing on modeling and understanding human communication, including speech, language, and gesture using computational and AI-based methods.
The position is financed by WASP, the Wallenberg AI, Autonomous Systems and Software Program and its entails participation in WASP doctoral school.