Metraipolis › archive › dc_39730a7261db

EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation — arXiv:2609.16011

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16011
License (as archived)
CC0-1.0
Archived
2026-10-15T21:30:44.818Z
SHA-256 of the archived text
c1791a1e3b9089e9397c8ad898d86617b1001ec9c661a80a9ab6954d01ca39ea
Stable URL of this page
https://metraipolis.com/documento/dc_39730a7261db

How to cite

EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation — arXiv:2609.16011 — arXiv (en), https://arxiv.org/abs/2609.16011 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39730a7261db (Metraipolis archive dc_39730a7261db, sha256 c1791a1e3b9089e9397c8ad898d86617b1001ec9c661a80a9ab6954d01ca39ea)
BibTeX
@misc{dc39730a7261db,
  title = {EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation — arXiv:2609.16011},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16011},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39730a7261db; sha256 c1791a1e3b9089e9397c8ad898d86617b1001ec9c661a80a9ab6954d01ca39ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16011. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Embodied conversational agents require synchronized full-body motion (body gestures and facial expressions) that aligns with speech and emotional state. Omni-modal large language models excel at multimodal understanding but produce only linguistic outputs, leaving a critical gap in embodied response generation. We identify and address a failure of emotion conditioning: like other conditional generators that under-use weak conditioning signals, a flow-matching model given both a rich audio embedding and a discrete emotion label suppresses the emotion, generating near-identical motion regardless of the specified emotion. We present EMODY Flow, a lightweight (around 35M parameters) flow-matching framework that attaches to a frozen Qwen-3 Omni model and reuses its internal Mimi audio-codecs to condition two parallel DiT generators - one for SMPL-X body pose, one for FLAME facial expressions. A training-time auxiliary emotion classifier restores emotion sensitivity by forcing generated motion to be emotion-identifiable. EMODY Flow sets a new state of the art on BEAT2 gesture quality, with FGD 0.302, Beat Correlation 0.853, and Diversity 24.62 - improving over the best prior results by 26%, 5%, and 62% respectively - and transfers to zero-shot facial animation on TFHP without domain-specific fine-tuning. Beyond these quantitative gains, the classifier yields clearly emotion-separated motion, which we demonstrate qualitatively through a multidimensional-scaling analysis of the generated gestures.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-16 in cs.RO).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM); Robotics (cs.RO); Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.16011 — 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 2026-10-15T21:30:17.386Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).