IWAENC Keynote Talk and 5 Papers

5 July 2024, by David Mosteller

Happy to announce a Keynote talk of Timo Gerkmann for IWAENC 2024
"Next-Generation Speech Enhancement: Generative Diffusion Models and End-to-End Multichannel Filtering"

As well as the following peer-reviewed paper presentations

• Alina Mannanova, Kristina Tesch, Jean-Marie Lemercier, Timo Gerkmann, "Meta-Learning for Variable Array Configurations in End-to-End Few-Shot Multichannel Speech Enhancement", Int. Workshop on Acoustic Enhancement (IWAENC), Aalborg, Denmark, Sep. 2024.
• Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki, "Buddy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models", Int. Workshop on Acoustic Enhancement (IWAENC), Aalborg, Denmark, Sep. 2024. [arxiv]
• Danilo de Oliveira, Eric Grinstein, Patrick Naylor, Timo Gerkmann, "Laser: Language-Queried Speech Enhancer", Int. Workshop on Acoustic Enhancement (IWAENC), Aalborg, Denmark, Sep. 2024.
• Bunlong Lay, Sebastian Zaczek, Timo Gerkmann, "Robustness of Speech Separation Models for Similar-pitch Speakers", Int. Workshop on Acoustic Enhancement (IWAENC), Aalborg, Denmark, Sep. 2024.
• Huajian Fang, Timo Gerkmann, "Uncertainty-Based Remixing for Unsupervised Domain Adaptation in Deep Speech Enhancement", Int. Workshop on Acoustic Enhancement (IWAENC), Aalborg, Denmark, Sep. 2024.