Simon Welker
Scholar

Simon Welker

Google Scholar ID: If3qsuwAAAAJ
Universität Hamburg
Deep learningSpeech processingGenerative modelingX-ray imagingPtychography
Google Scholar↗
Citations & Impact
All-time
Citations
1,016
 
H-index
14
 
i10-index
18
 
Publications
20
 
Co-authors
19
list available
Contact
No contact links provided.
Publications
8 items
Real-Time Streamable Generative Speech Restoration with Flow Matching
2025
Cited
0
Diffusion Buffer for Online Generative Speech Enhancement
2025
Cited
0
Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference
2025
Cited
0
Real-Time Streaming Mel Vocoding with Generative Flow Matching
2025
Cited
0
FlowDec: A flow-based full-band general audio codec with high perceptual quality
2025
Cited
0
Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech
arXiv.org · 2024
Cited
2
Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models
arXiv.org · 2024
Cited
1
Speech Enhancement and Dereverberation With Diffusion-Based Generative Models
IEEE/ACM Transactions on Audio Speech and Language Processing · 2022
Cited
266
Resume (English only)
Co-authors
19 total
Timo Gerkmann
Timo Gerkmann
Signal Processing, Computer Science Department, Universität Hamburg, Germany
Julius Richter
Julius Richter
Meta
Jean-Marie Lemercier
Jean-Marie Lemercier
NVIDIA
Tal Peer
Tal Peer
Signal Processing, University of Hamburg
Vesa Välimäki
Vesa Välimäki
Professor of Audio Signal Processing, Aalto University, Espoo, Finland
Eloi Moliner Juanpere
Eloi Moliner Juanpere
Aalto University
Henry Chapman
Henry Chapman
Center for Free-Electron Laser Science, DESY & University of Hamburg
Yi-Chiao, Wu
Yi-Chiao, Wu
Meta