Sebastian Braun
Principal Researcher
About
My research interests are in the field of audio and acoustic signal processing using AI, e.g. audio enhancement, separation, analysis and generation. I have deep background in microphone array processing, acoustic localization and tracking, acoustic parameter estimation, perceptual acoustics and spatial audio. I am following the principle that – whenever possible – any audio algorithm and model should be real-time capable for interactive and compute efficient use.
I work closely with product teams at Microsoft to develop algorithms on various audio applications, for example enhancing speech and audio by separating unwanted sound like echo, noise, reverberation and interfering speakers, to improve captured speech signal quality and intelligibility for human and machine listeners, or analyze and understand sound robustly.
Academic career
2018-present: Researcher at Microsoft Research
2018: Research intern at Microsoft Research
2012-2018: PhD (Dr.-Ing.) at the International Audio Laboratories Erlangen (opens in new tab) (FAU Erlangen (opens in new tab) in collaboration with Fraunhofer IIS (opens in new tab)). Thesis “Speech dereverberation in noisy environments using time-frequency domain signal models (opens in new tab)”
2017: Research visit at MUSAE Lab (opens in new tab) at INRS (opens in new tab), Montreal, Canada.
2006-2012: Bsc and Msc (Dipl.-Ing.) in electrical and sound engineering at TU (opens in new tab) and KU (opens in new tab) Graz, Austria