@inproceedings{zhang-etal-2025-orchestrating,
    title = "Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis",
    author = "Zhang, Yehang  and
      Xu, Xinli  and
      Xu, Xiaojie  and
      Zhang, Doudou  and
      Liu, Li  and
      Chen, Ying-Cong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-luhme/2025.emnlp-main.1133/",
    doi = "10.18653/v1/2025.emnlp-main.1133",
    pages = "22278--22293",
    ISBN = "979-8-89176-332-6",
    abstract = "Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media. However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, audio diversity and the absence of dedicated datasets. While existing methods excel in short videos, they falter in long scenarios (e.g., movies) due to fragmented synthesis and inadequate cross-scene consistency. We propose LVAS-Agent, a multi-agent framework that offers a coordinated, multi-component approach to long-video audio generation. Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, audio design and audio synthesis. To enable systematic evaluation, we introduce LVAS-Bench, the first benchmark with 207 professionally curated long videos spanning diverse scenarios. Experiments show that our method outperforms state-of-the-art V2A models in overall audio synthesis quality."
}