Picture for Sangshin Oh

Sangshin Oh

A Demand-Driven Perspective on Generative Audio AI

Add code
Jul 10, 2023
Figure 1 for A Demand-Driven Perspective on Generative Audio AI
Figure 2 for A Demand-Driven Perspective on Generative Audio AI
Figure 3 for A Demand-Driven Perspective on Generative Audio AI
Figure 4 for A Demand-Driven Perspective on Generative Audio AI
Viaarxiv icon

FALL-E: A Foley Sound Synthesis Model and Strategies

Add code
Jun 16, 2023
Viaarxiv icon

A Proposal for Foley Sound Synthesis Challenge

Add code
Jul 21, 2022
Viaarxiv icon

ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergence

Add code
May 09, 2022
Figure 1 for ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergence
Figure 2 for ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergence
Figure 3 for ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergence
Figure 4 for ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergence
Viaarxiv icon

Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations

Add code
Jul 26, 2021
Figure 1 for Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
Figure 2 for Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
Figure 3 for Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
Figure 4 for Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
Viaarxiv icon