Picture for Zhongweiyang Xu

Zhongweiyang Xu

Multi-Source Music Generation with Latent Diffusion

Add code
Sep 10, 2024
Viaarxiv icon

FoVNet: Configurable Field-of-View Speech Enhancement with Low Computation and Distortion for Smart Glasses

Add code
Aug 12, 2024
Viaarxiv icon

uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models

Add code
Oct 02, 2023
Viaarxiv icon

Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions

Add code
Sep 16, 2023
Viaarxiv icon

SpatialCodec: Neural Spatial Speech Coding

Add code
Sep 14, 2023
Figure 1 for SpatialCodec: Neural Spatial Speech Coding
Figure 2 for SpatialCodec: Neural Spatial Speech Coding
Figure 3 for SpatialCodec: Neural Spatial Speech Coding
Viaarxiv icon

Learning to Separate Voices by Spatial Regions

Add code
Jul 15, 2022
Figure 1 for Learning to Separate Voices by Spatial Regions
Figure 2 for Learning to Separate Voices by Spatial Regions
Figure 3 for Learning to Separate Voices by Spatial Regions
Figure 4 for Learning to Separate Voices by Spatial Regions
Viaarxiv icon

Dual-path Attention is All You Need for Audio-Visual Speech Extraction

Add code
Jul 09, 2022
Figure 1 for Dual-path Attention is All You Need for Audio-Visual Speech Extraction
Figure 2 for Dual-path Attention is All You Need for Audio-Visual Speech Extraction
Figure 3 for Dual-path Attention is All You Need for Audio-Visual Speech Extraction
Viaarxiv icon