Dynamic Restrained Uncertainty Weighting Loss For Multitask Learning Of Vocal Expression

Abstract

We propose a novel Dynamic Restrained Uncertainty Weighting Loss to experimentally handle the problem of balancing the contributions of multiple tasks on the ICML ExVo 2022 Challenge. The multitask aims to recognize expressed emotions and demographic traits from vocal bursts jointly. Our strategy combines the advantages of Uncertainty Weight and Dynamic Weight Average, by extending weights with a restraint term to make the learning process more explainable. We use a lightweight multi-exit CNN architecture to implement our proposed loss approach. The experimental H-Mean score (0.394) shows a substantial improvement over the baseline H-Mean score (0.335).

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysong2022dynamic

Related papers

• Self-supervised Attention Networks And Uncertainty Loss Weighting For Multi-task Emotion Recognition On Vocal Bursts (2022)0.00
• Multitask Vocal Burst Modeling With Resnets And Pre-trained Paralinguistic Conformers (2022)0.00
• End-to-end Multimodal Emotion And Gender Recognition With Dynamic Joint Loss Weights (2018)0.00
• Self-supervision And Learnable Strfs For Age, Emotion, And Country Prediction (2022)0.00
• An Efficient Multitask Learning Architecture For Affective Vocal Burst Analysis (2022)0.00
• Burst2vec: An Adversarial Multi-task Approach For Predicting Emotion, Age, And Origin From Vocal Bursts (2022)0.00
• Comparing Supervised And Self-supervised Embedding For Exvo Multi-task Learning Track (2022)0.00
• Attention-augmented End-to-end Multi-task Learning For Emotion Prediction From Speech (2019)13.50