Picture for Gerard Sant

Gerard Sant

Enhancing Crowdsourced Audio for Text-to-Speech Models

Add code
Oct 17, 2024
Figure 1 for Enhancing Crowdsourced Audio for Text-to-Speech Models
Figure 2 for Enhancing Crowdsourced Audio for Text-to-Speech Models
Figure 3 for Enhancing Crowdsourced Audio for Text-to-Speech Models
Figure 4 for Enhancing Crowdsourced Audio for Text-to-Speech Models
Viaarxiv icon

Pose-Based Sign Language Appearance Transfer

Add code
Oct 17, 2024
Viaarxiv icon

SignCLIP: Connecting Text and Sign Language by Contrastive Learning

Add code
Jul 01, 2024
Viaarxiv icon

Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation

Add code
May 14, 2022
Figure 1 for Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
Figure 2 for Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
Figure 3 for Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
Figure 4 for Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
Viaarxiv icon