logo Idiap Research Institute        
 [BibTeX] [Marc21]
Comparing supervised and self-supervised embedding for ExVo Multi-Task learning track
Type of publication: Conference paper
Citation: Purohit_ICML_2022
Publication status: Accepted
Booktitle: Proceedings of the ICML Expressive Vocalizations Workshop held in conjunction with the 39th International Conference on Machine Learning
Year: 2022
Location: Maryland, USA
Abstract: 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.
Keywords: Emotion Recognition, Expressive Vocalizations, Multi-task learning, Self-supervised embedding
Projects EMIL
Authors Purohit, Tilak
Ben Mahmoud, Imen
Vlasenko, Bogdan
Magimai.-Doss, Mathew
Added by: [UNK]
Total mark: 0
  • Purohit_ICML_2022.pdf