Research interests

• Inverse problems
• X-ray imaging / Ptychography
• Generative models for signal restoration

Publications

1. Simon Welker, Lorenz Kuger, Tim Roith, Berthy Feng, Martin Burger, Timo Gerkmann, Henry Chapman, "Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference", accepted for SIAM Journal on Imaging Sciences, 2026. [arxiv] [code]
2. Simon Welker, Bunlong Lay, Maris Hillemann, Tal Peer, Timo Gerkmann, "Real-Time Streamable Generative Speech Restoration with Flow Matching", accepted for IEEE Transactions on Audio, Speech, and Language Processsing, 2026. [arxiv] [audio] [code]
3. Simon Welker, Bunlong Lay, Maris Hillemann, Tal Peer, Timo Gerkmann, "Flow matching for real-time joint speech enhancement and bandwidth extension," Show-and-Tell Demo at IEEE ICASSP, Barcelona, Spain, April 2026. [info] [paper] [video]
4. Simon Welker, Tal Peer, Timo Gerkmann, "Real-Time Streaming Mel Vocoding with Generative Flow Matching", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Barcelona, Spain, May 2026. [arxiv] [code]
   
   2025
   
   
5. Simon Welker, Maris Hillemann, Tal Peer, Timo Gerkmann, "Real-Time Diffusion Demo for Speech Enhancement with 48ms Latency," Demo at ITG Conference on Speech Communication, Berlin, Germany, September 2025. [paper] [video]
6. Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, "Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech", Proc. of Interspeech, Rotterdam, The Netherlands, Aug. 2025. [doi], [arxiv], [code]
7. Jean-Marie Lemercier, Eloi Moliner, Simon Welker, Vesa Välimäki, Timo Gerkmann, "Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models", IEEE Trans. Audio, Speech, Language Proc., Vol. 33, pp. 2244-2258, 2025. [doi] [arxiv] [audio] [code]
8. Simon Welker, Matthew Le, Ricky T. Q. Chen, Wei-Ning Hsu, Timo Gerkmann, Alexander Richard, Yi-Chiao Wu, "FlowDec: A flow-based full-band general audio codec with high perceptual quality," International Conference on Learning Representations (ICLR), Singapore, Apr. 2025.
   [openreview]
   
   2024
   
   
9. Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, Vesa Välimäki, Timo Gerkmann, "Diffusion Models for Audio Restoration: A review [Special Issue On Model-Based and Data-Driven Audio Signal Processing]," IEEE Signal Processing Magazine, vol. 41, no. 6, pp. 72-84, Nov. 2024.
   [DOI] [arXiv]
10. Danilo de Oliveira, Simon Welker, Julius Richter, Timo Gerkmann, "The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement," ISCA Interspeech, Kos, Greece, September 2024.
    [DOI] [arXiv]
11. Julius Richter, Yi-Chiao Wu, Steven Krenn, Simon Welker, Bunlong Lay, Shinji Watanabe, Alexander Richard, Timo Gerkmann, "EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation," ISCA Interspeech, Kos, Greece, September 2024.
    [DOI] [arXiv] [Audio] [Code]
12. Simon Welker, Tal Peer, Henry N. Chapman, Timo Gerkmann, "Live Iterative Ptychography with projection-based algorithms," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea, April 2024.
    [DOI] [arXiv] [Code]
13. Tal Peer, Simon Welker, Johannes Kolhoff, Timo Gerkmann, "A Flexible Online Framework for Projection-Based STFT Phase Retrieval," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea, April 2024.
    [DOI] [arXiv]
14. Navin Raj Prabhu, Bunlong Lay, Simon Welker, Nale Lehmann-Willenbrock, Timo Gerkmann, "EMOCONV-Diff: Diffusion-Based Speech Emotion Conversion for Non-Parallel and in-the-Wild Data," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea, April 2024.
    [DOI] [arXiv]
15. Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Tal Peer, Timo Gerkmann, "Causal Diffusion Models for Generalized Speech Enhancement," IEEE Open Journal of Signal Processing, vol. 5, pp 780-789, 2024.
    [DOI] [Audio]
16. Simon Welker, Henry N. Chapman, Timo Gerkmann, "DriftRec: Adapting diffusion models to blind JPEG restoration," IEEE Transactions on Image Processing (TIP), vol. 33, pp 2795-2807, 2024.
    [DOI] [arXiv]
17. Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki, "BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models," 18th International Workshop on Acoustic Signal Enhancement (IWAENC), Aalborg, Denmark, September 2024.
    [DOI] [arXiv] [Audio] [Code]
    
    2023
    
    
18. Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, "Diffusion Posterior Sampling for Informed Single-Channel Dereverberation," IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, 2023.
    [DOI] [arXiv]
19. Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, "StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation," IEEE/ACM Transactions on Audio, Speech, Language Processing, vol. 31, pp. 2724 -2737, 2023.
    [DOI] [arXiv] [Audio] [Code]
20. Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann, "Speech Enhancement and Dereverberation with Diffusion-Based Generative Models," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2351 - 2364, 2023.
    [DOI] [arXiv] [Audio] [Code]
21. Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Tal Peer, Timo Gerkmann, "Speech Signal Improvement Using Causal Generative Diffusion Models," IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, Greece, June 2023.
    [DOI] [arXiv] [Audio]
22. Tal Peer, Simon Welker, Timo Gerkmann, "DiffPhase: Generative Diffusion-Based STFT Phase Retrieval," IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, Greece, June 2023.
    [DOI] [arXiv]
23. Bunlong Lay, Simon Welker, Julius Richter, Timo Gerkmann "Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement", ISCA Interspeech, Dublin, Ireland, August 2023.
    [DOI] [arXiv] [Audio] [Code]
24. Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, "Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration," IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, Greece, June 2023.
    [DOI] [arXiv]
    
    2022
    
    
25. Simon Welker, Julius Richter, Timo Gerkmann, "Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain," ISCA Interspeech, Incheon, Korea, Sep. 2022.
    [DOI] [arXiv] [Audio] [Code]
26. Simon Welker, Henry N. Chapman, Timo Gerkmann, "Blind Drifting: Diffusion models with a linear SDE drift term for blind image restoration tasks," NeurIPS 2022 Workshop "The Symbiosis of Deep Learning and Differential Equations II" (DLDE II), December 2022.
    [OpenReview]
27. Tal Peer, Simon Welker, Timo Gerkmann, "Beyond Griffin-Lim: Improved Iterative Phase Retrieval for Speech," 17th International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg, Germany, September 2022.
    [DOI] [arXiv]
28. Simon Welker, Tal Peer, Henry N. Chapman, Timo Gerkmann, "Deep Iterative Phase Retrieval for Ptychography," IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Singapore, May 2022.
    [DOI] [arXiv]