Universität Hamburg - der Forschung, der Lehre, der Bildung, zur Homepage
Signal Processing (SP)
Department of InformaticsSignal Processing (SP)

Photo: Timo Gerkmann/SP

Signal Processing

Jean-Marie Lemercier, MSc

lemercier

Photo: lemercier

Hearing Devices

Signal Processing (SP)

Address

Universität Hamburg
Department of Informatics
SP Research Group

Office

Room: F-124

Contact

Tel: +49 40 42883-2538

Research interests

  • Model-based Speech Dereverberation for Hearing Aids
  • Speech Enhancement with Diffusion Models
  • Diffusion-based Methods for Speech Inverse Problems

  1. Jean-Marie Lemercier, Eloi Moliner, Simon Welker, Vesa Välimäki, Timo Gerkmann, "Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models", submitted to IEEE TASLP, 2024, [arxiv][code][audio]
  2. Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki, "BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models ", IWAENC, Sep. 2024 [arxiv][code][audio]
  3. Jean-Marie Lemercier, Simon Rouard, Jade Copet, Yossi Adi, Alexandre Défossez, "An Independence-promoting Loss for Music Generation with Language Models", ICML, Jul. 2024 [arxiv][audio][code]
  4. Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, Vesa Välimäki, Timo Gerkmann, "Diffusion Models for Audio Restoration", IEEE Signal Processing Magazine, Jan. 2025 [arxiv]
  5. Bunlong Lay, Jean-Marie Lemercier, Julius Richter, Timo Gerkmann, "Single and Few-step Diffusion for Generative Speech Enhancement ", ICASSP Apr. 2024 [arxiv]
  6. Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, "Diffusion Posterior Sampling for Informed Single-Channel Dereverberation", Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, USA, Oct. 2023
  7. Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann, "Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Model", VDE 15th ITG Conference on Speech Communication, Aachen, Germany, 2023 [arxiv][code][audio]
  8. Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Tal Peer, Timo Gerkmann, "On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings", VDE 15th ITG Conference on Speech Communication, Aachen, Germany, 2023 [arxiv]
  9.  Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Tal Peer, Timo Gerkmann, "Speech Signal Improvement Using Causal Generative Diffusion Model, ICASSP May 2023 [arxiv]
  10. Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, "StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation", IEEE/ACM Trans. Audio, Speech, Language Proc. [arxiv][code][audio]
  11. Jean-Marie Lemercier, Julian Tobergte, Timo Gerkmann, "Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation", ISCA Interspeech, Dublin, Ireland, Aug. 2023. [arxiv]
  12. Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann, "Speech Enhancement and Dereverberation with Diffusion-based Generative Models", IEEE/ACM Trans. Audio, Speech, Language Proc.  [arxiv] [code] [audio][doi]
  13. Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, "Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Rhodes Island, Greece, Jun 2023. [arxiv][code][audio] [doi]
  14. Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann, "A Neural Network-supported Two-Stage Algorithm for Lightweight Dereverberation on Hearing Devices", EURASIP Journal on Audio, Speech, and Music Processing, Vol 18, 2023. [arxiv][audio][doi]
  15. Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann, "Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments", ISCA Interspeech, Incheon, Korea, Sep. 2022 [arxiv][doi]
  16. Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann "Customizable End-to-End Optimization of Online Neural Network-Supported Derverberation for Hearing Devices", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Singapore, Jun. 2022 [arxiv][audio][doi]
  17. Jean-Marie Lemercier, Leroy Bartel, David Ditter and Timo Gerkmann, "An Integrated Deep-Clustering Based System for Speaker Count Agnostic Speech Separation", ITG Conference on Speech Communication, Kiel, Germany, Sep. 2021 [doi]