Learning Subjective Time-Series Data via Utopia Label Distribution Approximation

no code implementations • 15 Jul 2023 • Wenxin Xu, Hexin Jiang, Xuefeng Liang, Ying Zhou, Yin Zhao, Jie Zhang

In this work, we propose Utopia Label Distribution Approximation (ULDA) for time-series data, which makes the training label distribution closer to real-world but unknown (utopia) label distribution.

Age Estimation Depth Estimation +4

Gaussian-smoothed Imbalance Data Improves Speech Emotion Recognition

no code implementations • 17 Feb 2023 • Xuefeng Liang, Hexin Jiang, Wenxin Xu, Ying Zhou

We find the data distribution in the IEMOCAP dataset is very imbalanced, which may harm models to learn a better representation.

Data Augmentation Speech Emotion Recognition