Papers

This page lists the papers related to the URGENT 2024 Challenge or those experimented with the URGENT Challenge data.

  1. [2024-09] Wangyou Zhang, Robin Scheibler, Kohei Saijo, Samuele Cornell, Chenda Li, Zhaoheng Ni, Jan Pirklbauer, Marvin Sach, Shinji Watanabe, Tim Fingscheidt, Yanmin Qian, “URGENT Challenge: Universality, Robustness, and Generalizability for Speech Enhancement,” in Proc. ISCA Interspeech, 2024, pp. 4868–4872.

    Preliminary exploration of the URGENT Challenge design, including data preprocessing and simulation, baseline framework, and evaluation protocol.

  2. [2025-06] Wangyou Zhang, Kohei Saijo, Samuele Cornell, Robin Scheibler, Chenda Li, Zhaoheng Ni, Anurag Kumar, Marvin Sach, Wei Wang, Yihui Fu, Shinji Watanabe, Tim Fingscheidt, and Qian Yanmin, “Lessons Learned from the URGENT 2024 Speech Enhancement Challenge,” in Proc. ISCA Interspeech, 2025, pp. 853–857.

    Initial analysis of the URGENT 2024 Challenge outcomes, focusing on the data and evaluation metric design.

  3. [2025-??] Wangyou Zhang, Kohei Saijo, Samuele Cornell, Robin Scheibler, Chenda Li, Zhaoheng Ni, Anurag Kumar, Marvin Sach, Wei Wang, Yihui Fu,Xiaohuai Le, Zhihang Sun, Xiaobin Rong, Rong Chao, Shinji Watanabe, Tim Fingscheidt, and Yanmin Qian, “Datasets and Learnings in the 2024 URGENT Speech Enhancement Challenge,” Submitted to NeurIPS 2025.

    Official summary of the URGENT 2024 Challenge, including system descriptions of top-ranking teams, comprehensive analysis of model behavior, and other findings from the challenge.

  4. [2025-05] Sanberk Serbest, Tijana Stojkovic, Milos Cernak, Andrew Harper, “DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration,” arXiv preprint arXiv:2505.23515, 2025.

    A new model evaluated on the URGENT 2024 Challenge non-blind test set.