We present a vision-infused method that can deal with both audio-only and audio-visual associated inpainting Inspired by image inpainting, called Vision-Infused Audio Inpainter (VIAI).
The MUSICES dataset can be accessed here.
We are still sorting out the code. For now it is not complete thus not runable, but the architecture is revealed. Please wait for more details.
The use of this software is RESTRICTED to non-commercial research and educational purposes.
@InProceedings{Zhou_2019_ICCV,
author = {Zhou, Hang and Liu, Ziwei and Xu, Xudong and Luo, Ping and Wang, Xiaogang},
title = {Vision-Infused Deep Audio Inpainting},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}
The structure of this codebase is borrowed from pix2pix and wavent_vocoder.