Silvia Arellano Garcia

I am a first year PhD student at the Division of Speech, Music and Hearing, supervised by Gustav Eje Henter, Jonas Beskow and Hedvig Kjellström. My research focuses on AI for 3D gesture motion. More broadly, my research interests lie in deep generative models for animation applications, including motion synthesis. My research is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP)

Previous experience

I received my BSc in Electrical Engineering from Universitat Politècnica de Catalunya (UPC) and my MSc in Machine Learning from KTH. During my studies, I interned at Dolby Laboratories, building AI models to generate Room Impulse Responses (RIR) conditioned on acoustic parameters, and at SEED (Electronic Arts), where I completed my MSc thesis on multiview 3D reconstruction. Prior to starting my PhD, I worked as an ML Engineer at EA Sports, focusing primarily on pose estimation and computer vision.

I am open to collaborations and supervising MSc students who want to work on generative AI projects!