Metraipolis › archive › dc_60f33ba7df28
AISHELL8-FISHEYE: A Fisheye Audio-Visual Dataset for Target Speaker Extraction with Distortion-Aware Baselines — arXiv:2611.09368
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09368
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T23:04:21.523Z
- SHA-256 of the archived text
9fc8e0e9ecbf4e608d028c49375a5ecb28f42b252e4ef801338fc8438ce27b87- Stable URL of this page
https://metraipolis.com/documento/dc_60f33ba7df28
How to cite
AISHELL8-FISHEYE: A Fisheye Audio-Visual Dataset for Target Speaker Extraction with Distortion-Aware Baselines — arXiv:2611.09368 — arXiv (en), https://arxiv.org/abs/2611.09368 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_60f33ba7df28 (Metraipolis archive dc_60f33ba7df28, sha256 9fc8e0e9ecbf4e608d028c49375a5ecb28f42b252e4ef801338fc8438ce27b87)
BibTeX
@misc{dc60f33ba7df28,
title = {AISHELL8-FISHEYE: A Fisheye Audio-Visual Dataset for Target Speaker Extraction with Distortion-Aware Baselines — arXiv:2611.09368},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09368},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_60f33ba7df28; sha256 9fc8e0e9ecbf4e608d028c49375a5ecb28f42b252e4ef801338fc8438ce27b87},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09368. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fisheye cameras offer wide visual coverage but distort facial and lip geometry, challenging audio-visual target speaker extraction. We introduce AISHELL8-FISHEYE, a 47.03-hour corpus of 94 Mandarin speakers with synchronized audio and paired fisheye and normal-camera videos. Speaker-disjoint splits and synthetic two-speaker mixtures support reproducible evaluation under matched acoustic conditions. We also establish a baseline that combines a lip-reading encoder with a frozen distortion-aware branch transferred from fisheye head pose estimation. On fisheye video, adding this branch to an adapted lip encoder improves scale-invariant signal-to-distortion ratio improvement from 10.47 to 11.84 dB. The branch does not improve performance with a frozen lip encoder, highlighting the importance of visual adaptation. A substantial gap to paired normal-camera inputs remains. The corpus and baseline resources support further research on speech extraction from distorted visual cues. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2611.09368 — 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 2026-11-09T22:59:22.100Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).