Sindhu Hegde's repositories
pseudo-visual-speech-denoising
Official code for the paper "Visual Speech Enhancement Without A Real Visual Stream" published at WACV 2021
speaker-separation
Code for the cocktail-party problem of isolating and enhancing the speech for the target speaker
video-super-resolver
Official code for the paper "Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors" published at ACM-MM 2022
lip2speech
Official code for the paper "Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild" published at ACM-MM 2022
avobjects
Implementation for ECCV20 paper "Self-Supervised Learning of audio-visual objects from video"
DMALab
Data Mining and Analysis Lab
gestsync_webpage
Code for the website of GestSync paper
image_processing_workshop_kletech
Image Processing & Computer Vision basics: Notebooks (questions with solutions).
ml_lab_ecsc_306
LabExample
Sindhu-Hegde.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
Speech-enhancement
Deep neural network based speech enhancement toolkit