Metraipolis › archive › dc_b8ca64b078eb

DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors — arXiv:2609.36624

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36624
License (as archived)
CC0-1.0
Archived
2026-10-07T16:22:48.649Z
SHA-256 of the archived text
e9a389101edad2a68571068bea9a862e186f947fd3e898d033bee6c2fbdf29ad
Stable URL of this page
https://metraipolis.com/documento/dc_b8ca64b078eb

How to cite

DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors — arXiv:2609.36624 — arXiv (en), https://arxiv.org/abs/2609.36624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8ca64b078eb (Metraipolis archive dc_b8ca64b078eb, sha256 e9a389101edad2a68571068bea9a862e186f947fd3e898d033bee6c2fbdf29ad)
BibTeX
@misc{dcb8ca64b078eb,
  title = {DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors — arXiv:2609.36624},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36624},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8ca64b078eb; sha256 e9a389101edad2a68571068bea9a862e186f947fd3e898d033bee6c2fbdf29ad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Joint speech-gesture synthesis must coordinate two modalities despite limited paired data. Existing approaches often lack bidirectional interaction, have limited language coverage, or simplify body and finger representations. We present DualTrack, which couples pretrained speech and motion priors on a shared 12.5 Hz timeline. Causal adapters exchange previous-packet information, while current-state fusion coordinates the streams before they separately complete sixteen-codebook packets. We evaluate 43 BEAT2 recordings in four languages, with speakers held out from joint training and validation. On the shared English/Spanish inputs, without speech or motion prefixes, DualTrack achieves lower word error rate and full-motion Fréchet Gesture Distance, higher beat consistency and speech naturalness than the evaluated GELINA baseline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36624 — 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 2026-10-07T15:54:53.519Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).