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

Photo: Timo Gerkmann/SP

Signal Processing

Bunlong Lay, MSc

lay

Photo: lay

Speech and Audio Signal Processing

Signal Processing (SP)

Address

Universität Hamburg
Department of Informatics
SP Research Group

Office

Room: F-125

Contact

Tel: +49 40 42883-2549

Research interests

  • Single-Channel Speech Enhancement
  • Diffusion-based models

  1. 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, Aug. 2023 [arxiv][audio][code]
  2. Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Tal Peer, Timo Gerkmann, "Speech Signal Improvement Using Causal Generative Diffusion Models", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Rhodes, Greece, Jun. 2023. [arxiv]
  3. Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann, "Speech Enhancement and Dereverberation with Diffusion-Based Generative Models", submitted to IEEE/ACM Trans. on Audio, Speech, Language Proc. (TASLP) [arxiv] [audio] [code]
  4. Bunlong Lay, Timo Gerkmann, "Speech Enhancement Regularized by a Speaker Verification Model", Int. Workshop on Multimedia Signal Processing (MMSP), Shanghai, China, Sep. 2022. [doi]