@inproceedings{li-etal-2026-finelap,
    title = "{F}ine{LAP}: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining",
    author = "Li, Xiquan  and
      Xu, Xuenan  and
      Ma, Ziyang  and
      Chen, Wenxi  and
      He, Haolin  and
      Kong, Qiuqiang  and
      Chen, Xie",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.473/",
    pages = "10393--10408",
    ISBN = "979-8-89176-390-6",
    abstract = "Contrastively pretrained audio{--}language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks.Existing extensions fail to exploit the varying granularity of real-world audio{--}text data, where massive clip-level textual descriptions coexist with limited frame-level annotations. This paper proposes **Fine**-grained **L**anguage-**A**udio **P**retraining (**FineLAP**), a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data.FineLAP introduces a dual-stream sigmoid loss with a cluster-based sampling strategy to jointly learn from clip- and frame-level supervision. To capture both global semantics and local details, FineLAP uses a decoupled audio projector on top of a self-supervised encoder.To alleviate the scarcity of temporally annotated data, we present FineLAP-100k, a large-scale synthetic SED dataset constructed through a scalable curation pipeline.Extensive experiments demonstrate that FineLAP achieves SOTA performance across multiple audio understanding tasks, including retrieval, classification, sound event detection, and text-to-audio grounding. Ablation studies further show that coarse- and fine-grained alignment are mutually beneficial, providing insights for building better audio-language models (ALMs)."
}