PhD position in generative AI and expressive speech synthesis for social inclusion
KTH has a fully funded PhD position in generative AI and expressive speech synthesis for social inclusion.
The task of the candidate is to develop and evaluate the usefulness of a generative AI and expressive
speech synthesis in Augmentative Communication Technology for individuals with communication disabilities.
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 system will leverage the KTH spontaneous TTS used in the video below and with more samples here : www.speech.kth.se/tts-demos/