Metraipolis › archive › dc_1541b4d0eea0

Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition — arXiv:2609.10394

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10394
License (as archived)
CC0-1.0
Archived
2026-10-16T11:00:16.053Z
SHA-256 of the archived text
0c96003a867caf6a48d6b2a444eadea871e6a883daa6c904c92a71d8e1044ada
Stable URL of this page
https://metraipolis.com/documento/dc_1541b4d0eea0

How to cite

Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition — arXiv:2609.10394 — arXiv (en), https://arxiv.org/abs/2609.10394 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1541b4d0eea0 (Metraipolis archive dc_1541b4d0eea0, sha256 0c96003a867caf6a48d6b2a444eadea871e6a883daa6c904c92a71d8e1044ada)
BibTeX
@misc{dc1541b4d0eea0,
  title = {Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition — arXiv:2609.10394},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10394},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1541b4d0eea0; sha256 0c96003a867caf6a48d6b2a444eadea871e6a883daa6c904c92a71d8e1044ada},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10394. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the complexity of natural conversation, which involves overlapping speech, spontaneous turn-taking, unscripted vocabulary and variable acoustic conditions. To shift the field toward realistic dialogue, we introduce Candor-LR, a conversational benchmark derived from the CANDOR corpus of 1,656 natural dyadic videoconferences. Our custom data preparation pipeline yields 713.5, 10.1, and 60.1 hours of training, validation, and test data, respectively. Evaluating pretrained AVSR models on Candor-LR reveals that audio-only accuracy drops sharply compared to LRS3, but visual cues compensate effectively, driving much larger performance gains on Candor-LR than on LRS3. Furthermore, training on this corpus significantly improves cross-domain robustness under both clean and noisy conditions, as its realistic conversational data captures broader audio-video features. We open-source our pipeline to ensure reproducibility, establishing Candor-LR as a challenging benchmark for conversational AVSR.

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/2609.10394 — 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 2026-10-16T10:02:34.443Z 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).