Picture for Joan Serrà

Joan Serrà

Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility

Add code
Sep 14, 2024
Viaarxiv icon

Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity

Add code
Jul 15, 2024
Viaarxiv icon

Sequential Contrastive Audio-Visual Learning

Add code
Jul 08, 2024
Viaarxiv icon

GASS: Generalizing Audio Source Separation with Large-scale Data

Add code
Sep 29, 2023
Viaarxiv icon

Mono-to-stereo through parametric stereo generation

Add code
Jun 26, 2023
Viaarxiv icon

CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models

Add code
Jun 16, 2023
Viaarxiv icon

Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation

Add code
Oct 26, 2022
Viaarxiv icon

Full-band General Audio Synthesis with Score-based Diffusion

Add code
Oct 26, 2022
Viaarxiv icon

Universal Speech Enhancement with Score-based Diffusion

Add code
Jun 07, 2022
Figure 1 for Universal Speech Enhancement with Score-based Diffusion
Figure 2 for Universal Speech Enhancement with Score-based Diffusion
Figure 3 for Universal Speech Enhancement with Score-based Diffusion
Figure 4 for Universal Speech Enhancement with Score-based Diffusion
Viaarxiv icon

On loss functions and evaluation metrics for music source separation

Add code
Feb 16, 2022
Figure 1 for On loss functions and evaluation metrics for music source separation
Figure 2 for On loss functions and evaluation metrics for music source separation
Figure 3 for On loss functions and evaluation metrics for music source separation
Figure 4 for On loss functions and evaluation metrics for music source separation
Viaarxiv icon