Deep Long Audio Inpainting
This work addresses audio inpainting, a neglected area compared to image/video, for applications in audio editing and recovery, though it appears incremental as it adapts existing methods.
The paper tackles the challenging problem of long audio inpainting (>200 ms) for audio editing and transmission loss recovery by adapting deep learning frameworks from audio synthesis and image inpainting, setting up a benchmark and analyzing factors like mask size and receptive field.
Long (> 200 ms) audio inpainting, to recover a long missing part in an audio segment, could be widely applied to audio editing tasks and transmission loss recovery. It is a very challenging problem due to the high dimensional, complex and non-correlated audio features. While deep learning models have made tremendous progress in image and video inpainting, audio inpainting did not attract much attention. In this work, we take a pioneering step, exploring the possibility of adapting deep learning frameworks from various domains inclusive of audio synthesis and image inpainting for audio inpainting. Also, as the first to systematically analyze factors affecting audio inpainting performance, we explore how factors ranging from mask size, receptive field and audio representation could affect the performance. We also set up a benchmark for long audio inpainting. The code will be available on GitHub upon accepted.