Abstract
Abstract
The choice of a loss function is a critical part in machine learning. This paper evaluates two different loss functions commonly used in regression-task dimensional speech emotion recognition — error-based and correlation-based loss functions. We found that using correlation-based loss function with concordance correlation coefficient (CCC) loss resulted in better performance than error-based loss functions with mean squared error (MSE) and mean absolute error (MAE). The evaluations were measured in averaged CCC among three emotional attributes. The results are consistent with two input feature sets and two datasets. The scatter plots of test prediction by those two loss functions also confirmed the results measured by CCC scores.
Subject
General Physics and Astronomy
Cited by
23 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Optimizing HMI for Intelligent Electric Vehicles Using BCI and Deep Neural Networks with Genetic Algorithms;World Electric Vehicle Journal;2024-07-27
2. Modeling Continuous Emotions in Text Data using IEMOCAP Database;2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP);2024-07-11
3. Speech Emotion Recognition In Continuous Space Using IEMOCAP Database;2024 IEEE 12th International Symposium on Signal, Image, Video and Communications (ISIVC);2024-05-21
4. Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
5. Incongruity-Aware Cross-Modal Attention for Audio-Visual Fusion in Dimensional Emotion Recognition;IEEE Journal of Selected Topics in Signal Processing;2024-04