Metraipolis › archive › dc_ce0eb73528fc
The Shape of Speech: A Geometric Measure of Coarticulation for Speech-Driven 3D Facial Animation — arXiv:2610.03436
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.03436
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:09:42.829Z
- SHA-256 of the archived text
a2cc3eea06fb793806e4da85efab83f1b7bca7f77a75dca7d864fdd70c7ba814- Stable URL of this page
https://metraipolis.com/documento/dc_ce0eb73528fc
How to cite
The Shape of Speech: A Geometric Measure of Coarticulation for Speech-Driven 3D Facial Animation — arXiv:2610.03436 — arXiv (en), https://arxiv.org/abs/2610.03436 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce0eb73528fc (Metraipolis archive dc_ce0eb73528fc, sha256 a2cc3eea06fb793806e4da85efab83f1b7bca7f77a75dca7d864fdd70c7ba814)
BibTeX
@misc{dcce0eb73528fc,
title = {The Shape of Speech: A Geometric Measure of Coarticulation for Speech-Driven 3D Facial Animation — arXiv:2610.03436},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.03436},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce0eb73528fc; sha256 a2cc3eea06fb793806e4da85efab83f1b7bca7f77a75dca7d864fdd70c7ba814},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03436. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speech-driven 3D facial animation can reproduce recognizable mouth poses. However, it can simplify the motion between them, and that motion carries coarticulation, the way the sounds around each sound shape its articulation. We introduce a geometric measure of this trajectory shaping: lip-path length compared with the shortest route through the vowel, consonant and vowel positions of a speech segment. In contrast to the endpoint chord, this consonant-aware route accounts for obligatory transit and avoids degeneracy, while preserving invariance to uniform motion gain. The measure needs only a forced alignment, so it applies where no ground truth exists. We demonstrate it on four state-of-the-art methods, one per architectural family, real-time and offline. All four trace flatter lip trajectories than captured speech. Against frame-rate-matched ground truth, DiffPoseTalk, ARTalk and FaceFormer show clear deficits, equivalent on this measure to removing 15-60% of real speech's fast articulatory component. CodeTalker is marginal on the primary measure and clear on a companion measure. A pre-registered study with 97 viewers and 3,523 judgments underpins the measured direction: controlled damping of real motion lowers the score and is penalized, whereas exaggeration shows no detected penalty over the tested range. Viewers also prefer real speech in 73.4% of sentence comparisons and, in the aggregate, on single words. Together, the measure, its calibration and the study identify a perceptually relevant loss of trajectory shaping and a concrete target for improving synthesized articulation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV). Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2610.03436 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T08:21:44.309Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).