Unsupervised Improvement of Audio-Text Cross-Modal Representations.
arXiv (Cornell University)（2023）
关键词
Audio-text representation learning,data augmentation,contrastive learning,sound event classification,acoustic scene classification
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要