Leveraging hierarchical attention and dynamic fusion mechanisms for multi-modal speech emotion recognition
Authors:
- Zengzhao ChenZCZengzhao Chen
- Chuanxu ZhaoCZChuanxu Zhao
- Zhifeng WangZWZhifeng Wang
- Chuan LiuCLChuan Liu
- Qiuyu ZhengQZQiuyu Zheng
- Jianwen SunJSJianwen Sun
- 18 February 2026
- journal article
- Published by Elsevier in Applied Soft Computing
- Vol. 193
Abstract
No abstract availableFunding Information
- Central China Normal University (CCNU25ai003)
- National Natural Science Foundation of China (62477022)
- National Natural Science Foundation of China (62577027)
- National Natural Science Foundation of China (62177022)
- National Key Research and Development Program of China (2022ZD0117103)
This publication has 23 references indexed in Scilit:
- Automatic Speech Emotion Recognition: a Systematic Literature ReviewInternational Journal of Speech Technology, 2024
- Learning facial expression and body gesture visual information for video emotion recognitionExpert Systems with Applications, 2023
- Multimodal sentiment analysis based on fusion methods: A surveyInformation Fusion, 2023
- Learning multi-scale features for speech emotion recognition with connection attention mechanismExpert Systems with Applications, 2022
- RecogNet-LSTM+CNN: a hybrid network with attention mechanism for aspect categorization and sentiment classificationJournal of Intelligent Information Systems, 2022
- Attention-based multimodal contextual fusion for sentiment and emotion classification using bidirectional LSTMMultimedia Tools and Applications, 2021
- Speech emotion recognition using deep 1D & 2D CNN LSTM networksBiomedical Signal Processing and Control, 2019
- A survey of multimodal sentiment analysisImage and Vision Computing, 2017
- Building emotional dictionary for sentiment analysis of online newsWorld Wide Web, 2013
- IEMOCAP: interactive emotional dyadic motion capture databaseLanguage Resources and Evaluation, 2008