Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression

06/22/2022
by   Meishu Song, et al.
0

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).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2022

The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts

The ICML Expressive Vocalization (ExVo) Competition is focused on unders...
research
07/14/2022

Proceedings of the ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts

This is the Proceedings of the ICML Expressive Vocalization (ExVo) Compe...
research
09/28/2022

An Efficient Multitask Learning Architecture for Affective Vocal Burst Analysis

Affective speech analysis is an ongoing topic of research. A relatively ...
research
11/07/2017

GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks

Deep multitask networks, in which one neural network produces multiple p...
research
06/06/2023

FAMO: Fast Adaptive Multitask Optimization

One of the grand enduring goals of AI is to create generalist agents tha...
research
09/23/2022

Grouped Adaptive Loss Weighting for Person Search

Person search is an integrated task of multiple sub-tasks such as foregr...
research
03/30/2021

Continuous Weight Balancing

We propose a simple method by which to choose sample weights for problem...

Please sign up or login with your details

Forgot password? Click here to reset