2 papers
cs.SD2026
Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval
HaeJun Yoo, Yongseop Shin, Insung Lee +2
Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-…
cs.SD2026
CAF-Score: Calibrating CLAP with LALMs for Reference-free Audio Captioning Evaluation
Insung Lee, Taeyoung Jeong, Haejun Yoo +2
While Large Audio-Language Models (LALMs) have advanced audio captioning, robust evaluation remains difficult. Reference-based metrics are expensive and often fail to assess acoust…