Publications
2022
- Learning to Separate Voices by Spatial Regions. [paper] [demo]
Zhongweiyang Xu, Romit Roy Choudhury.
In The Thirty-ninth International Conference on Machine Learning (ICML 2022)
2023
Dual-path Attention is All You Need for Audio-Visual Speech Extraction. [paper]
Zhongweiyang Xu*, Xulin Fan*, Mark Hasegawa-Johnson.
In The Fourty-eighth IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)TaBE: Decoupling spatial and spectral processing with Taylor’s unfolding method in the beamspace domain for multi-channel speech enhancement. [paper]
Andong Li, Guochen Yu, Zhongweiyang Xu, Cunhang Fan, Xiaodong Li, Chengshi Zheng.
In Information Fusion, Volume 101, January 2024, 101976MULTI-CHANNEL SPEECH ENHANCEMENT FOR SPEAR CHALLENGE: A THREE STAGE APPROACH. [paper]
Zhongweiyang Xu, Debottam Dutta, Xulin Fan, Mark Hasegawa-Johnson, Romit Roy Choudhury.
Rank 2nd in [SPEAR Challenge]SpatialCodec: Neural Spatial Speech Coding. [paper] [demo] [code]
Zhongweiyang Xu, Yong Xu, Vinay Kothapally, Heming Wang, Muqiao Yang, Dong Yu.
(ICASSP2024)Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions. [paper] [demo]
Heming Wang, Meng Yu, Hao Zhang, Chunlei Zhang, Zhongweiyang Xu, Muqiao Yang, Yixuan Zhang, Dong Yu.
(Preprint)uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models. [paper] [demo]
Muqiao Yang, Chunlei Zhang, Yong Xu, Zhongweiyang Xu, Heming Wang, Bhiksha Raj, Dong Yu.
(ICASSP2024)