PhD Colloquium: Robust Speech Enhancement Using Statistical Signal Processing and Machine-Learning

27 April 2018

Abstract. In many applications, e.g., hearing aids, human-machine interfaces, and tele-communications, speech signals are of particular interest. In noisy environments, the quality of speech signals suffers from additional noise captured by the microphones. For recovering the speech signal, single-channel speech enhancement algorithms are employed.

In this work, synergies between ma-chine-learning and statistical signal processing are exploited to increase the robustness and performance of these algorithms.

Friday, 27 April 2018, 14:00, Room D-220, Informatikum

Speaker: Robert Rehr, PhD Candidate at group SP