I'm Jilt Sebastian, currently working as a Senior Research Scientist at Mobius Labs GmbH, Berlin. Previously I was a Research Engineer, Speech Technology at Telepathy Labs, GmBH, Zurich. I received dual degree doctorate (Masters and Ph.D) in Computer Science from Indian Institute of Technology Madras under the supervision of Prof. Hema A. Murthy working in Speech and Music Technology Lab. I was also a pre-doctoral fellow in Speech and Audio Processing Group, Idiap Research Institute, Switzerland. I received Bachelor's degree in Electronics and & Communcation Engineering (Hons.) from Mahatma Gandhi Univeristy, Kerala.

I am currently working on automatic speech recognition from videos. I am responsible for audio R&D at mobius and I build models for various audio-related tasks. Previously, I have worked on audio classification, multi-modal emotion recognition and sentiment analysis, raw-waveform and phase-based features for audio and spike analysis, with recent focus on end-to-end systems for regression and classification tasks.