The positions are placed in the Division of Speech, Music and Hearing at KTH.
This particular project aims to create new machine learning that addresses real needs in science and applications. Particular focus areas are audio and speech synthesis, and motion synthesis from motion-capture data (e.g., for animation and games). Mathematically, you will primarily work to create and use deep-learning-based probabilistic time-series models. Important concepts are attention and normalising flows (a relative of GANs). Outside machine learning and probability theory the research involves topics from signal processing, NLP, phonetics, and computer graphics.
There are two positions available.