Picture for Tianshu Qu

Tianshu Qu

Cross-attention Inspired Selective State Space Models for Target Sound Extraction

Add code
Sep 10, 2024
Figure 1 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Figure 2 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Figure 3 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Figure 4 for Cross-attention Inspired Selective State Space Models for Target Sound Extraction
Viaarxiv icon

Leveraging Moving Sound Source Trajectories for Universal Sound Separation

Add code
Sep 07, 2024
Figure 1 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Figure 2 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Figure 3 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Figure 4 for Leveraging Moving Sound Source Trajectories for Universal Sound Separation
Viaarxiv icon

TT-Net: Dual-path transformer based sound field translation in the spherical harmonic domain

Add code
Oct 30, 2022
Viaarxiv icon

Room geometry blind inference based on the localization of real sound source and first order reflections

Add code
Jul 22, 2022
Figure 1 for Room geometry blind inference based on the localization of real sound source and first order reflections
Figure 2 for Room geometry blind inference based on the localization of real sound source and first order reflections
Figure 3 for Room geometry blind inference based on the localization of real sound source and first order reflections
Figure 4 for Room geometry blind inference based on the localization of real sound source and first order reflections
Viaarxiv icon

Direct source and early reflections localization using deep deconvolution network under reverberant environment

Add code
Oct 22, 2021
Figure 1 for Direct source and early reflections localization using deep deconvolution network under reverberant environment
Figure 2 for Direct source and early reflections localization using deep deconvolution network under reverberant environment
Figure 3 for Direct source and early reflections localization using deep deconvolution network under reverberant environment
Figure 4 for Direct source and early reflections localization using deep deconvolution network under reverberant environment
Viaarxiv icon