Metraipolis › archive › dc_cf55453b24ce

Co-Speech with You: Training-Free Personalization of Robot Co-Speech Gestures — arXiv:2609.13876

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13876
License (as archived)
CC0-1.0
Archived
2026-10-16T02:14:27.536Z
SHA-256 of the archived text
fcee683f6bc6a76d8422cf4843e37fb6247116c65e9465f80513921e93389982
Stable URL of this page
https://metraipolis.com/documento/dc_cf55453b24ce

How to cite

Co-Speech with You: Training-Free Personalization of Robot Co-Speech Gestures — arXiv:2609.13876 — arXiv (en), https://arxiv.org/abs/2609.13876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf55453b24ce (Metraipolis archive dc_cf55453b24ce, sha256 fcee683f6bc6a76d8422cf4843e37fb6247116c65e9465f80513921e93389982)
BibTeX
@misc{dccf55453b24ce,
  title = {Co-Speech with You: Training-Free Personalization of Robot Co-Speech Gestures — arXiv:2609.13876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf55453b24ce; sha256 fcee683f6bc6a76d8422cf4843e37fb6247116c65e9465f80513921e93389982},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Personal robots should adapt their co-speech gesture style to a new user without requiring model retraining. We present a training-free personalization pipeline that combines a frozen audio-conditioned diffusion prior with a gesture style encoder and lightweight conditioning adapters. The encoder is first trained to discriminate speaker identities and then jointly refined with the adapters using the diffusion objective, enabling a reusable style embedding to be extracted from approximately 10 seconds of enrollment motion through a single forward pass. To support this setting, we also release a Quest~3 capture application and a dataset of spontaneous co-speech motion from ten participants. We evaluate the system on held-out speakers using Style Recognition Accuracy (SRA) and Fr'echet Gesture Distance (FGD) to measure personalization and motion quality. Our approach improves SRA from 27.6\% for the frozen prior to 69.5\% while preserving motion quality (FGD 34.2 versus 34.8), and replacing the enrollment embedding with another person's reduces SRA to 11.4\%. The generated gestures are retargeted to a physical NAO robot, and this improvement also transfers to the robot deployment setting, where speech is synthesized using five TTS voices, retaining 67.3\% SRA.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.13876 — 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 2026-10-16T01:52:32.309Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).