Metraipolis › archive › dc_7e6b68fc7669

Open-Set Ego-Noise Separation for Legged-Robot Audition via Annotation-Free Adaptation and Pretrained-Model Transfer — arXiv:2609.07440

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07440
License (as archived)
CC0-1.0
Archived
2026-10-16T15:31:07.656Z
SHA-256 of the archived text
5a2e976dc6fa850e4922691f2bb1bb5b79e9d1377be6c49f038aa2a1e5346f1f
Stable URL of this page
https://metraipolis.com/documento/dc_7e6b68fc7669

How to cite

Open-Set Ego-Noise Separation for Legged-Robot Audition via Annotation-Free Adaptation and Pretrained-Model Transfer — arXiv:2609.07440 — arXiv (en), https://arxiv.org/abs/2609.07440 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e6b68fc7669 (Metraipolis archive dc_7e6b68fc7669, sha256 5a2e976dc6fa850e4922691f2bb1bb5b79e9d1377be6c49f038aa2a1e5346f1f)
BibTeX
@misc{dc7e6b68fc7669,
  title = {Open-Set Ego-Noise Separation for Legged-Robot Audition via Annotation-Free Adaptation and Pretrained-Model Transfer — arXiv:2609.07440},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07440},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e6b68fc7669; sha256 5a2e976dc6fa850e4922691f2bb1bb5b79e9d1377be6c49f038aa2a1e5346f1f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07440. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper proposes an open-set ego-noise separation framework for legged-robot audition via annotation-free adaptation and pretrained-model transfer. The framework removes robot-specific ego-noise while preserving environmental sounds whose classes are not specified in advance. Acoustic sensing provides cues about a robot's surroundings beyond the visual field, but walking-induced ego-noise from footstep impacts, joint-backlash rattling, and motor noise severely contaminates the recordings. The framework first uses RecurGraph to select ego-noise-dominant clips from the unlabeled recordings by aggregating clip embeddings into an embedding centroid and propagating scores over an audio-embedding graph. The selected clips are mixed with diverse environmental sounds from a large-scale sound-event dataset to provide paired mixture--target supervision for open-set separation. Transfer-DiT then adapts a general-purpose zero-shot neural separator to achieve high-fidelity open-set ego-noise separation for the target robot. Experiments with bipedal and quadrupedal robots show reliable clip selection and improvements in separation quality and downstream task performance over baseline separators. These results demonstrate the feasibility of annotation-free adaptation without separately recorded ego-noise-only data or manual clip-level annotations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.07440 — 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 2026-10-16T15:11:47.587Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).