CONF Purohit_ICML_2022/IDIAP Comparing supervised and self-supervised embedding for ExVo Multi-Task learning track Purohit, Tilak Ben Mahmoud, Imen Vlasenko, Bogdan Magimai.-Doss, Mathew Emotion Recognition Expressive Vocalizations Multi-task learning Self-supervised embedding EXTERNAL https://publications.idiap.ch/attachments/papers/2022/Purohit_ICML_2022.pdf PUBLIC Proceedings of the ICML Expressive Vocalizations Workshop held in conjunction with the 39th International Conference on Machine Learning Maryland, USA 2022 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 an hybrid approach, where predictions derived via both SSL and task-specific supervised learning are used. Our best system on test-set surpass the ComPARE baseline (harmonic-mean of all sub-task scores i.e., S_MLT) by a relative 13% margin.