@inproceedings{yoo-etal-2026-omni,
    title = "Omni-Embed-Audio: Leveraging Multimodal {LLM}s for Robust Audio-Text Retrieval",
    author = "Yoo, HaeJun  and
      Shin, Yongseop  and
      Lee, Insung  and
      Koo, Myoung-Wan  and
      Chang, Du-Seong",
    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.1038/",
    pages = "22664--22680",
    ISBN = "979-8-89176-390-6",
    abstract = "Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world search behavior, limiting their assessment of practical retrieval robustness. We present Omni-Embed-Audio (OEA), a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding. To systematically evaluate robustness beyond caption-style queries, we introduce User-Intent Queries (UIQs){---}five formulations reflecting natural search behaviors: questions, commands, keyword tags, paraphrases, and exclusion-based negative queries. For negative queries, we develop a hard negative mining pipeline and propose discrimination metrics (HNSR, TFR) assessing models' ability to suppress acoustically similar distractors. Experiments on AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas: (1) dominant text-to-text retrieval (+22{\%} relative improvement), and (2) substantially superior hard negative discrimination (+4.3{\%}p HNSR@10, +34.7{\%} relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries."
}