跳到正文
原文
arXiv · Audio and Speech· Lucas H. Ueda, Jo\~ao G. T. Lima, Paula D. P. Costa·· 3 小时前AI 评分28

Crab:通过多层对比监督提升语音情感识别在自然语音与表演语音下的表现

Crab: Multi Layer Contrastive Supervision to Improve Speech Emotion Recognition Under Both Acted and Natural Speech Condition

AI 导读

summary_zh: Crab(Contrastive Representation and Multimodal Aligned Bottleneck)提出多层对比监督(MLCS)策略。

来源:arXiv · Audio and Speech · arxiv.org