Human-CLAP: Human-perception-based contrastive language-audio pretraining

arXiv:2506.23553v3 Announce Type: replace-cross 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 evaluati...

🔗 Read more: https://arxiv.org/abs/2506.23553

#News #Psychology #Policy #Biology #Academic