The paper presents "Draw an Audio," a controllable video-to-audio synthesis model addressing audio-visual synchronization challenges using Mask-Attention and Time-Loudness modules, achieving state-of-the-art results.

https://arxiv.org/abs//2409.06135

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers