معرفی
Prof. Timo Gerkmann is a Professor at the University of Hamburg's Department of Informatics, leading the Signal Processing Research Group. His research focuses on statistical signal processing and machine learning for speech and audio applications, including communication devices, hearing aids, audiovisual media, and human-machine interfaces. He previously held roles at Technicolor Research & Innovation, KTH Royal Institute of Technology, and Siemens Corporate Research. His work emphasizes generative models, diffusion-based approaches, and acoustic signal enhancement. He currently serves as Senior Area Editor of the IEEE/ACM Transactions on Audio, Speech, and Language Processing.
Research Interests:
- Statistical Signal Processing for Speech and Audio
- Machine Learning Applications in Acoustic Environments
- Diffusion Models for Audio Restoration
- Audio-Visual Speech Enhancement
- Human-Machine Interaction Systems
- Acoustic Scene Analysis
Publications Highlight Trends: Recent works focus on diffusion models for speech enhancement, generative approaches to dereverberation, and audiovisual multimodal analysis. He has pioneered frameworks like ReverbFX datasets and FlowDec codecs, emphasizing perceptual quality and unsupervised domain adaptation.
Advising & Grants: While no specific students or grants are listed, his research group actively publishes in top venues, indicating sustained academic contributions. His work bridges theoretical signal processing with applied systems engineering.
Labs/Teams: Leads the Signal Processing (SP) Research Group at UHH, specializing in cutting-edge audio technologies and human-centric signal processing solutions.
