Reproduce “AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Ju-Chieh Chou, Chung-Ming Chien, Karen Livescu

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.