Nikita Torgashov

I'm a first-year PhD student working on Conversational AI in the Department of Speech, Music and Hearing (TMH), supervised by Gabriel Skantze and Gustav Eje Henter. My current focus lies in the field of streaming Text-to-Speech, where I'm trying to make it very responsive and intelligible.

Past

Before that, I worked as a machine learning engineer in speech processing, specializing in speaker recognition and voice anti-spoofing at IDR&D. I was involved in multiple open-source projects, such as ReDimNet and VoxTube.  I obtained my Master's Degree in Machine Learning and Data Analysis from ITMO University.