Gustav Henter

MSc students thesis projects available at this link: www.kth.se/profile/ghe/page/msc-thesis-proposals (The page is only visible if you are logged in to KTH.se, else the link gives error 404.)

I am an assistant professor in intelligent systems – specifically machine learning – at the Division of Speech, Music and Hearing (TMH). My primary research interests are deep generative models (a.k.a. “generative AI”) for synthesis applications, particularly 1) speech synthesis (text-to-speech) and 2) data-driven 3D character animation (body motion and co-speech gesticulation). Applications of the former include virtual assistants, prostethic voices, phonetics research, and assistive technologies for the visually impaired, and for the latter films, games, virtual avatars, social robots, and research on human-computer interaction. My research is supported by the national Wallenberg AI, Autonomous Systems and Software Program (WASP) initiative, where I am recruited faculty and a core member of the WASP Research Arena for Media and Language (WARA M&L), and by the Ministry of Trade, Industry, and Energy (MOTIE), South Korea.

I completed my PhD at the Sound and Image Processing lab (SIP; later part of Communication Theory, which is now the Division of Information Science and Engineering) at the School of Electrical Engineering (EES) at KTH. I graduated in 2013 and moved on to a post-doc position at the Centre for Speech Technology Research (CSTR) at the University of Edinburgh, UK, followed by another post-doc in Prof. Junichi Yamagishi's research group at the National Institute of Informatics in Tokyo, Japan. I returned to KTH in April 2018, first as a post-doc and then, from January 2020, as an assistant professor. I have the degree of Docent.

For more information and resources, including full-text publications, presentations, etc., please see my professional homepage at KTH.

In addition to my position at KTH, I am also head of research at Motorica AB, a spin-off company dedicated to making 3D character animation easier and better, making our research on generative models of motion bring value to the world outside the lab.