ICLR and 3x ICASSP papers accepted

23 January 2025, by David Mosteller

We are pleased to announce the publication of our latest research in prominent academic conferences: one paper at the International Conference on Learning Representations (ICLR) and three papers at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP).

These publications demonstrate our ongoing commitment to excellence in research and development in the fields of machine learning and speech signal processing.

• 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]
• Julius Richter, Danilo de Oliveira, Timo Gerkmann, "Investigating Training Objectives for Generative Speech Enhancement," IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Hyderabad, India, Apr. 2025. [arxiv] [audio] [code]
• Etienne Thuillier, Jean-Marie Lemercier, Eloi Moliner, Timo Gerkmann, Vesa Välimäki, "HRTF Estimation using a Score-based Prior", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Hyderabad, India, Apr. 2025. [arxiv]
• Jakob Kienegger, Alina Mannanova and Timo Gerkmann, "Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Hyderabad, India, Apr. 2025. [arxiv]