Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval 文章

ArXiv CS.CL2026-06-02NEWSen作者: HaeJun Yoo, Yongseop Shin, Insung Lee, Myoung-Wan Koo, Du-Seong Chang
查看原文 →
关系图谱

Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval · 相关技术

相关技术

TFRHNSRhard negative mining pipelineUser-Intent Queriesmultimodal LLMsContrastive Language-Audio Pretraining