Signals 4 · free daily AI digest

AVSRBench: A Multi-Condition AVSR Benchmark

Paper recorded by Signals 4 on 2026-09-09 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-09 on arXiv · recorded by Signals 4 on 2026-09-10

Category: cs.CV · 计算机视觉 · first seen 2026-09-10

Abstract

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 lipsp

Read on arXiv →

#109 most recent of 237 cs.CV papers we have recorded · ↑ newer: Beyond Weak Labels: Prompt-Guided Local Refinement for Weakly Supervis · ↓ older: SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllab
Cite this page: AVSRBench: A Multi-Condition AVSR Benchmark: the #109 most recent of 237 cs.CV papers we have recorded (as of 2026-09-09). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/avsrbench-a-multi-condition-avsr-benchmark.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions