Metraipolis › archive › dc_edeb12e453ca

AVSRBench: A Multi-Condition AVSR Benchmark — arXiv:2609.10366

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.10366
License (as archived): CC0-1.0
Archived: 2026-10-16T11:00:15.148Z
SHA-256 of the archived text: a120a88b7a96bf7cfd681b15b9b5aef0861244ee1d717ddbc2aad9ca5a346ae3
Stable URL of this page: https://metraipolis.com/documento/dc_edeb12e453ca

How to cite

AVSRBench: A Multi-Condition AVSR Benchmark — arXiv:2609.10366 — arXiv (en), https://arxiv.org/abs/2609.10366 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edeb12e453ca (Metraipolis archive dc_edeb12e453ca, sha256 a120a88b7a96bf7cfd681b15b9b5aef0861244ee1d717ddbc2aad9ca5a346ae3)

BibTeX

@misc{dcedeb12e453ca,
  title = {AVSRBench: A Multi-Condition AVSR Benchmark — arXiv:2609.10366},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10366},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edeb12e453ca; sha256 a120a88b7a96bf7cfd681b15b9b5aef0861244ee1d717ddbc2aad9ca5a346ae3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10366. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain adaptation. To investigate this gap, we evaluate three AVSR architectures across six conditions: controlled broadcast speech, fixed-grammar utterances, hyper-articulated Lombard speech, read speech from professional lipspeakers and non-professional speakers, and spontaneous multi-party video conversations. We find that visual-only performance deteriorates rapidly beyond broadcast domains, and audio-video fusion mainly benefits Lombard speech environments. Visual understanding degrades sharply at 90° profile views, with multimodal systems relying largely on acoustic fallback. Additionally, speaker articulation proves more critical than minor camera shifts, and LLM-based architectures suffer from poor out-of-domain generalization. Our work highlights a significant generalization gap in current AVSR research. To address this, we also introduce RoomReader-AV as a new benchmark for AVSR and release a unified data preprocessing pipeline to make comprehensive multi-condition evaluation accessible.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2609.10366 — 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 2026-10-16T10:02:34.439Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).