# What Do Audio-Visual Synchronization Metrics Actually Measure?

arXiv: https://arxiv.org/abs/2608.25157 · HTML: https://mlsanity.com/paper/2608.25157/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 12 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [Synchformer: Efficient Synchronization from Sparse Cues](https://mlsanity.com/paper/2401.16423/) (2024)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)
- [Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation](https://mlsanity.com/paper/2309.16429/) (2023)
- [VABench: A Comprehensive Benchmark for Audio-Video Generation](https://mlsanity.com/paper/2512.09299/) (2025)
- [PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores](https://mlsanity.com/paper/2404.07336/) (2024)
- [STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models](https://mlsanity.com/paper/2403.09669/) (2024)
- [AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models](https://mlsanity.com/paper/2605.24652/) (2026)
- [SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation](https://mlsanity.com/paper/2603.29186/) (2026)

## Abstract (arXiv)

Automatic AV-sync metrics are widely used to rank and train audio-visual generators, but they are rarely audited as measurement instruments. We jointly audit AV-Align, ImageBind AV-relevance, JavisScore, and Synchformer/DeSync under a common reliability protocol: controlled-distortion monotonicity, preprocessing sensitivity, rank uncertainty, cross-metric agreement, PEAVS-proxy agreement, and learned fusion. The result is an axis split, not a single winner: Synchformer/DeSync is the strongest temporal-offset tracker (τ=0.84), ImageBind/JavisScore better match the PEAVS human-aligned proxy (τ=0.20) and content-disruption families, and AV-Align is the weakest standalone metric. The metrics mutually disagree (Krippendorff α=0.066), and neither linear nor simple k-NN fusion improves PEAVS agreement over the best individual metric. We recommend reporting AV-sync as a Reliability Card (metric-family breakdowns with confidence intervals) rather than a single bare synchronization score.