Comparing supervised and self-supervised embedding for ExVo Multi-Task learning track

arxiv(2022)

引用 0|浏览2
暂无评分
摘要
The ICML Expressive Vocalizations (ExVo) Multi-task challenge 2022, focuses on understanding the emotional facets of the non-linguistic vocalizations (vocal bursts (VB)). The objective of this challenge is to predict emotional intensities for VB, being a multi-task challenge it also requires to predict speakers' age and native-country. For this challenge we study and compare two distinct embedding spaces namely, self-supervised learning (SSL) based embeddings and task-specific supervised learning based embeddings. Towards that, we investigate feature representations obtained from several pre-trained SSL neural networks and task-specific supervised classification neural networks. Our studies show that the best performance is obtained with a hybrid approach, where predictions derived via both SSL and task-specific supervised learning are used. Our best system on test-set surpasses the ComPARE baseline (harmonic mean of all sub-task scores i.e., $S_{MTL}$) by a relative $13\%$ margin.
更多
查看译文
关键词
track,learning,self-supervised,multi-task
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