We are happy to announce 5 accepted original papers at ICASSP 2024 in Seoul!
Bunlong Lay, Jean-Marie Lemercier, Julius Richter, Timo Gerkmann, "SINGLE AND FEW-STEP DIFFUSION FOR GENERATIVE SPEECH ENHANCEMENT", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Seoul, South Korea, Apr. 2024. [arxiv]
Simon Welker, Tal Peer, Henry N. Chapman, Timo Gerkmann, "LIVE ITERATIVE PTYCHOGRAPHY WITH PROJECTION-BASED ALGORITHMS", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Seoul, South Korea, Apr. 2024. [arxiv]
Tal Peer, Simon Welker, Johannes Kolhoff, Timo Gerkmann, "A FLEXIBLE ONLINE FRAMEWORK FOR PROJECTION-BASED STFT PHASE RETRIEVAL", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Seoul, South Korea, Apr. 2024. [arxiv]
Navin Raj Prabhu, Bunlong Lay, Simon Welker, Nale Lehmann-Willenbrock, Timo Gerkmann, "EMOCONV-DIFF: DIFFUSION-BASED SPEECH EMOTION CONVERSION FOR NON-PARALLEL AND IN-THE-WILD DATA", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Seoul, South Korea, Apr. 2024. [arxiv]
Danilo de Oliveira, Timo Gerkmann, "DISTILLING HUBERT WITH LSTMS VIA DECOUPLED KNOWLEDGE DISTILLATION", IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Seoul, South Korea, Apr. 2024. [arxiv]