Picture for Sindhu B Hegde

Sindhu B Hegde

GestSync: Determining who is speaking without a talking head

Add code
Oct 08, 2023
Viaarxiv icon

Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild

Add code
Sep 01, 2022
Figure 1 for Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
Figure 2 for Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
Figure 3 for Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
Figure 4 for Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
Viaarxiv icon

Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors

Add code
Aug 17, 2022
Figure 1 for Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
Figure 2 for Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
Figure 3 for Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
Figure 4 for Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
Viaarxiv icon

Towards Automatic Speech to Sign Language Generation

Add code
Jun 24, 2021
Figure 1 for Towards Automatic Speech to Sign Language Generation
Figure 2 for Towards Automatic Speech to Sign Language Generation
Figure 3 for Towards Automatic Speech to Sign Language Generation
Figure 4 for Towards Automatic Speech to Sign Language Generation
Viaarxiv icon

Visual Speech Enhancement Without A Real Visual Stream

Add code
Dec 20, 2020
Figure 1 for Visual Speech Enhancement Without A Real Visual Stream
Figure 2 for Visual Speech Enhancement Without A Real Visual Stream
Figure 3 for Visual Speech Enhancement Without A Real Visual Stream
Figure 4 for Visual Speech Enhancement Without A Real Visual Stream
Viaarxiv icon