Human-CLAP: Human-perception-based contrastive language-audio pretraining
Abstract
Contrastive language-audio pretraining (CLAP) is widely used for audio generation and recognition tasks. For example, CLAPScore, which utilizes the similarity of CLAP embeddings, has been a major metric for the evaluation of the relevance between audio and text in text-to-audio. However, the relationship between CLAPScore and human subjective evaluation scores is still unclarified. We show that CLAPScore has a low correlation with human subjective evaluation scores. Additionally, we propose a human-perception-based CLAP called Human-CLAP by training a contrastive language-audio model using the subjective evaluation score. In our experiments, the results indicate that our Human-CLAP improved the Spearman's rank correlation coefficient (SRCC) between the CLAPScore and the subjective evaluation scores by more than 0.25 compared with the conventional CLAP.
Keywords
Cite
@article{arxiv.2506.23553,
title = {Human-CLAP: Human-perception-based contrastive language-audio pretraining},
author = {Taisei Takano and Yuki Okamoto and Yusuke Kanamori and Yuki Saito and Ryotaro Nagase and Hiroshi Saruwatari},
journal= {arXiv preprint arXiv:2506.23553},
year = {2026}
}
Comments
Submitted to APSIPA ASC 2025