arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.20064eess.AScs.SD
收藏

Odyssey情感识别挑战赛Task1的第一名解决方案:解决类别不平衡问题

1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem

Amazon(亚马逊)

Mingjie Chen, Hezhao Zhang, Yuanchao Li, Jiachen Luo, Wen Wu, Ziyang Ma, Peter Bell, Catherine Lai, Joshua Reiss, Lin Wang, Philip C. Woodland, Xie Chen, Huy Phan, Thomas Hain

AI总结:

本文针对Odyssey 2024情感识别挑战赛Task-1的类别不平衡问题,提出结合基于先验类别权重的focal loss与多数投票的7模型集成系统,在68个提交中排名第一,取得35.69%的Macro-F1分数。

摘要:

语音情感识别是一项针对自然情感语音的极具挑战性的分类任务,尤其是当训练和测试数据中情感类型的分布不平衡时。在这种情况下,模型更难学习区分少数类,导致这些类别有时被忽略或频繁被误分类。先前的工作在训练中使用了类别加权损失,但问题依然存在,因为它有时会导致少数类过拟合或多数类欠拟合。本文介绍了一个多站点团队为参加Odyssey 2024情感识别挑战赛Track-1而开发的系统。挑战赛数据具有上述特性,因此所提出的系统旨在通过在应用类别加权损失时在优化中引入focal loss来解决这些问题。具体而言,focal loss进一步由基于先验的类别权重加权。实验结果表明,结合这两种方法以牺牲多数类性能为代价带来了更好的整体性能。该系统进一步采用多数投票策略来结合7个模型集成的输出。这些模型独立训练,使用不同的声学特征和损失函数,目的是针对不同数据具有不同的属性。因此,这些模型在多数类和少数类上表现出不同的性能偏好。该集成系统输出在挑战赛中获得了最佳性能,在68个提交中排名第一。它也优于我们集合中的所有单一模型。在Odyssey 2024情感识别挑战赛Task-1数据上,该系统获得了35.69%的Macro-F1分数和37.32%的准确率。

英文摘要:

Speech emotion recognition is a challenging classification task with natural emotional speech, especially when the distribution of emotion types is imbalanced in the training and test data. In this case, it is more difficult for a model to learn to separate minority classes, resulting in those sometimes being ignored or frequently misclassified. Previous work has utilised class weighted loss for training, but problems remain as it sometimes causes over-fitting for minor classes or under-fitting for major classes. This paper presents the system developed by a multi-site team for the participation in the Odyssey 2024 Emotion Recognition Challenge Track-1. The challenge data has the aforementioned properties and therefore the presented systems aimed to tackle these issues, by introducing focal loss in optimisation when applying class weighted loss. Specifically, the focal loss is further weighted by prior-based class weights. Experimental results show that combining these two approaches brings better overall performance, by sacrificing performance on major classes. The system further employs a majority voting strategy to combine the outputs of an ensemble of 7 models. The models are trained independently, using different acoustic features and loss functions - with the aim to have different properties for different data. Hence these models show different performance preferences on major classes and minor classes. The ensemble system output obtained the best performance in the challenge, ranking top-1 among 68 submissions. It also outperformed all single models in our set. On the Odyssey 2024 Emotion Recognition Challenge Task-1 data the system obtained a Macro-F1 score of 35.69% and an accuracy of 37.32%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑