반응형
[Paper 리뷰] CLAP: Learning Audio Concepts from Natural Language Supervision
CLAP: Learning Audio Concepts from Natural Language SupervisionRestricted supervision 하에서 training 된 audio model은 flexibility의 한계가 있음CLAPNatural language supervision을 통해 audio concept을 학습2개의 encoder와 contrastive learning을 활용하여 audio, text description을 joint multimodal space로 modeling논문 (ICASSP 2023) : Paper Link1. Introduction대부분의 audio model은 specific task의 pre-defined category와 audio recording..
Paper/Representation
2025. 7. 30. 17:00
반응형