PRISM‑Bench is an audio‑centric diagnostic benchmark for text‑to‑audio‑video generation, built from 900 human‑verified samples. It evaluates audio along two axes—audio type (speech, music, sound) and sound‑source visibility (on‑screen vs. off‑screen)—across four perceptual dimensions (audio‑visual coherence, audio quality, audio expressiveness, and prompt following) using 35 fine‑grained criteria. The benchmark employs an enhanced MLLM‑as‑a‑Judge protocol that aligns strongly with human raters, revealing a performance gap between frontier and open‑source T2AV models and highlighting overfitting to perceptual fidelity while struggling with complex grounding and control tasks, especially for music and synchronized on‑screen audio.
By Yuchen Sun, Qian Yang, Jun Wang, Detai Xin, Guoqiao Yu, Guanglu Wan, Qi Jia
AVC-Reward introduces an event‑centric framework for evaluating audio‑video consistency, breaking down scenes into individual audio and visual events and assessing them at three levels: global narrative harmony, event‑level temporal synchronization, and fine‑grained attribute alignment. The metric, instantiated as a trainable reward model, is validated against human judgments using the AVC‑Benchmark, which contains diverse positive and negative samples from various generation models. AVC‑Reward outperforms existing automatic methods, offers interpretable failure localization, and enhances consistency when used as a reinforcement‑learning signal.
By Yuruo Wu, Kaihang Pan, Kai Shen, Jiacheng Li, Shuyuan Tu, Jisheng Dang, Li Tuoyu, Juncheng Li, Siliang Tang
arXiv:2609.08275v1 Announce Type: new
Abstract: Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute e...
By Tianyi Zeng, Junchao Liao, Yujie Wei, Ziying Zhang, Litao Li, Tianyi Wang, Zhichao Wei, Shuyao Xu, Wenwen Qiang, Siyu Zhu, Zhenghao Zhang, Long Qin
The paper introduces Cue2Narrate, a two‑stage pipeline that jointly predicts what visual events to narrate and when to insert the narration in long, untrimmed movie clips. It uses a dual‑head audio‑visual localizer to identify visual cue and narration windows, followed by a LoRA‑adapted vision‑language model that generates concise audio descriptions, trained with a Description Ranking Loss. The authors also present the LongLSMDC benchmark, comprising up to 8‑minute clips, and show that Cue2Narrate outperforms video‑only and audio‑only baselines by 5–12 points in average mAP and improves AD generation over fine‑tuned base VLMs.
By Akshita Gupta, Aditya Arora, Federico Tombari, Marcus Rohrbach, Anna Rohrbach
arXiv:2512.23994v5 Announce Type: replace-cross
Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to...
By Tianxin Xie, Wentao Lei, Kai Jiang, Guanjie Huang, Pengfei Zhang, Chunhui Zhang, Fengji Ma, Haoyu He, Han Zhang, Jiangshan He, Jinting Wang, Linghan Fang, Lufei Gao, Orkesh Ablet, Peihua Zhang, Ruolin Hu, Shengyu Li, Weilin Lin, Xiaoyang Feng, Xinyue Yang, Yan Rong, Yanyun Wang, Zihang Shao, Zelin Zhao, Chenxing Li, Shan Yang, Wenfu Wang, Meng Yu, Dong Yu, Li Liu
AVC-Reward introduces an event‑centric framework for evaluating audio‑video consistency in joint generation models. It separates audio and visual events, assesses them independently, cross‑validates cross‑modal relations, and aggregates results into a three‑level metric covering global narrative harmony, event‑level synchronization, and fine‑grained attribute alignment. The resulting AVC‑Reward model aligns closely with human judgments, offers interpretable failure localization, and enhances consistency when used as a reinforcement‑learning signal.
arXiv:2605.07593v2 Announce Type: replace
Abstract: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory str...
By Hengyi Feng, Hao Liang, Mingrui Chen, Bohan Zeng, Meiyi Qiang, Zhengyang Zhao, Zimo Meng, Zeang Sheng, Wentao Zhang
arXiv:2607. 16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes.
By Florian Schmid, Paul Primus, Alexander Fichtinger, Tara Jadidi, Tobias Morocutti, Gerhard Widmer
Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visua...
arXiv:2607. 09973v1 Announce Type: cross Abstract: Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable variation, and remain efficient for practical workflows.
By M\'elodie Desbos, Yara Bahram, Eric Granger, Mohammadhadi Shateri
OmniCapBench is a new deep‑structured evaluation framework for audio‑visual captioning that replaces free‑form text predictions with sets of atomic, verifiable units across entity references, visual shots, and audio events. It uses deterministic constraint checks and localized LLM‑based semantic comparisons to provide reliable, fine‑grained scoring. With 786 densely annotated videos, the benchmark can distinguish perception errors such as temporal grounding failures, identity drift, cross‑modal misalignment, and hallucinations, revealing that current multimodal large language models excel at local perception but struggle with long‑horizon audio‑visual reasoning.
By Zhongyu Yang, Jiale Tao, Ruitao Chen, Zuhao Yang, Yingfang Yuan, Xueliang Zhao, Auden, Kai Wang, Shuai Shao, Biao Wang, Steve Yves, Qinglin Lu
SsgCaps is a publicly available dataset of human-engineered sound scenes, each paired with a precisely structured prompt that guides the sampling process. The prompts are drawn from a predefined action-based typology, enabling extensive yet plausible sampling. A comparative quantitative analysis shows only small differences between the open and private versions, supporting the recommendation of the open version for benchmarking sound scene generation algorithms.
By Modan Tailleur (LS2N), Junwon Lee (LS2N), Laurie M Heller (LS2N), Mathieu Lagrange (LS2N), Keunwoo Choi, Brian McFee, Keisuke Imoto, Yuki Okamoto