Team member Julius Richter successfully defended his PhD thesis on September 12, 2025; Huajian Fang was awarded a PhD degree for his thesis titled 'Model-Based Deep Speech...' on June 16, 2025. Additionally, three papers have been accepted by the Interspeech conference.
Research Experience
Research areas include but are not limited to: Traditional Speech Enhancement, Diffusion Models for Speech Enhancement, Non-linear Spatial Filtering, Variational Autoencoders for Speech Enhancement, Phase-Aware Signal Processing, Social Signal Processing.
Background
Focuses on the development of novel digital signal processing and machine learning algorithms, especially for speech, audio, and multimodal signals.