AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse

Yihuan Huang, Jun Xue, Liu Jiajun, Daixian Li, Tong Zhang, Zhuolin Yi, Yanzhen Ren, Kai Li

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on MLD-VCLiPS-AVSR · Chinese-Lips (Tencent Meeting)CER: 10.97 -> 9.65Improved
fine-tune on MLD-VCLiPS-AVSR · Chinese-Lips (Lark)CER: 18.53 -> 13.64Improved
fine-tune on MLD-VCLiPS-AVSR · Chinese-Lips (Zoom)CER: 9.22 -> 7.93Improved
fine-tune on MLD-VCLiPS-AVSR · MLD-VC testCER: 42.37 -> 13.91Improved
add online (transmitted) data to fine-tuning (ablation)LiPS-AVSR · Chinese-Lips (Zoom)CER: 10.53 -> 7.93Improved
add online (transmitted) data to fine-tuning (ablation)LiPS-AVSR · Chinese-Lips (Lark)CER: 15.52 -> 13.64Improved
add online (transmitted) data to fine-tuning (ablation)LiPS-AVSR · Chinese-Lips (Tencent Meeting)CER: 10.15 -> 9.65Improved
add hyper-expression (Lombard) data to fine-tuning (ablation)LiPS-AVSR · Chinese-Lips (Zoom)CER: 9.61 -> 7.93Improved
add hyper-expression (Lombard) data to fine-tuning (ablation)LiPS-AVSR · Chinese-Lips (Lark)CER: 14.48 -> 13.64Improved
add hyper-expression (Lombard) data to fine-tuning (ablation)LiPS-AVSR · Chinese-Lips (Tencent Meeting)CER: 10.01 -> 9.65Improved
evaluate on Lombard-Grid instead of LRS3 (Lombard-containing data) under ZoomAuto-AVSR · audio-visual ZoomWER: 33.09 -> 12.36Improved
add visual modality to audio-only under ZoommWhisper-Flamingo · LRS3 (Zoom)WER: 10.38 -> 9.22Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy