3 accepted Interspeech papers

15 June 2025, by David Mosteller

We are pleased to announce the acceptance of the following papers for presentation at Interspeech 2025, which will be held in Rotterdam, the Netherlands, in August 2025:

•  Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, "Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech" [arXiv], [code]
• Jakob Kienegger and Timo Gerkmann, "Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios". [arXiv], [video]
• Bunlong Lay, Rostilav Makarov, and Timo Gerkmann, "Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency". [arXiv]
• The third paper will also be showcased in a "Show and Tell" demo "Real-Time Diffusion Buffer for Speech Enhancement On A Laptop."  

Congratulations to all the authors on their accepted submissions!