Universal speech enhancement aims to handle input speech with different distortions and input formats. To tackle this challenge, we present TS-URGENet, a Three-Stage Universal, Robust, and Generalizable speech Enhancement Network. To address various distortions, the proposed system employs a novel three-stage architecture consisting of a filling stage, a separation stage, and a restoration stage. The filling stage mitigates packet loss by preliminarily filling lost regions under noise interference, ensuring signal continuity. The separation stage suppresses noise, reverberation, and clipping distortion to improve speech clarity. Finally, the restoration stage compensates for bandwidth limitation, codec artifacts, and residual packet loss distortion, refining the overall speech quality. Our proposed TS-URGENet achieved outstanding performance in the Interspeech 2025 URGENT Challenge, ranking 2nd in Track 1.
Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis
Institute for Creative Technologies, University of Southern California(南加州大学创意技术研究所);University of Southern California(南加州大学);School of Medicine, University of California Irvine(加州大学欧文分校医学院)
WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction
Shenzhen Research Institute of Big Data(深圳大数据研究院);School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)(香港中文大学(深圳)数据科学学院);Shanghai Jiao Tong University(上海交通大学);Tencent AI Lab(腾讯人工智能实验室)
Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition
Department of Electrical Engineering, National Tsing Hua University(国立交通大学电子工程系);Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所)
Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges
Carnegie Mellon University(卡内基梅隆大学);Paderborn University(帕德博恩大学);NVIDIA(NVIDIA公司);Meta;Johns Hopkins University(约翰霍普金斯大学);Mitsubishi Electric Research Laboratories(三菱电机研究实验室);Southern University of Science and Technology(南方科技大学)