Masahiro Yasuda

representation learning (1) contrastive learning (1) transfer learning (1) scene classification (1) self-supervised learning (1) audio classification (1) audio captioning (1) triplet loss (1) zero-shot inference (1) weakly supervised (1) acoustic event detection (1) crossmodal retrieval (1) sound effect retrieval (1) contrastive language-audio pretraining (1) masked modeling (1) audio-language representation (1) word selection (1) weak label (1) keyword estimation (1) sound retrieval (1)