文献类型：期刊文献

中文题名：结合性别信息的多任务语音情感识别

英文题名：Multi-task Speech Emotion Recognition Incorporating Gender Information

作者：姚佳[1];李冬冬[1];王喆[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2026

卷号：53

期号：1

起止页码：180

中文期刊名：计算机科学

外文期刊名：Computer Science

收录：;北大核心:【北大核心2023】；

基金：国家自然科学基金(62276098)。

语种：中文

中文关键词：语音情感识别;多任务学习;动态权重分配;自监督模型

外文关键词：Speech emotion recognition;Multi-task learning;Dynamic weight assignment;Self-supervised models

摘要：现有的语音情感识别方法通常依赖深度学习模型提取声学特征,但大多仅关注通用特征的建模,未能充分挖掘数据中与情感密切相关的先验知识。为此,提出了一种端到端的多任务学习框架,利用自监督预训练模型WavLM提取包含丰富情感信息的语音特征,并将性别识别作为辅助任务,以捕捉性别差异对情感识别的潜在影响。针对传统多任务学习框架中固定权重计算损失导致的学习不均衡问题,进一步提出了一种自适应温度系数的动态权重平均方法(Temperature-aware Dynamic Weight Averaging,TA-DWA)。该方法通过动态调整温度系数平衡不同任务的学习速度,并结合任务损失变化率实现更合理的权重分配。实验结果表明,在IEMOCAP和EMODB数据集上,所提方法显著提高了情感识别准确率,验证了性别识别作为辅助任务的有效性以及动态权重策略在多任务学习中的优势。
Existing methods for speech emotion recognition usually rely on deep learning models to extract acoustic features,but most of them focus only on modelling generic features,failing to fully explore a priori knowledge in the data that is closely related to emotion.To this end,this paper proposes an end-to-end multi-task learning framework that utilizes the self-supervised pre-training model WavLM to extract speech features rich in emotional information,and introduces gender recognition as an auxiliary task to account for the influence of gender differences on emotion recognition.To address the learning imbalance issue caused by the fixed weight calculation in traditional multi-task learning frameworks,this paper proposes a Temperature-aware Dynamic Weight Averaging(TA-DWA)method.This method balances the learning speeds of different tasks by dynamically adjusting the temperature coefficient and achieves more reasonable weight allocation by incorporating the rate of change in task losses.Experimental results on the IEMOCAP and EMODB datasets demonstrate that the proposed approach significantly improves emotion recognition accuracy.These findings validate the effectiveness of using gender recognition as an auxiliary task and highlight the advantages of the dynamic weighting strategy in multi-task learning.