Reproduce “The Shape of Speech: A Geometric Measure of Coarticulation for Speech-Driven 3D Facial Animation” 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
Danzel Serrano, Przemyslaw Musialski
The authors introduce Rpw, a measure of lip-path shaping through vowel–consonant–vowel waypoints, to assess speech-driven 3D facial animation beyond endpoint poses. Using phone timings, it compares the lip trajectory with the shortest route through those waypoints. In a VOCASET comparison, DiffPoseTalk showed a +0.043 median deficit versus matched captured speech; this result does not establish generality or predict viewer preferences.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.