Enhancing Task-Specific Feature Learning with LLMs for Multimodal Emotion and Intent Joint Understanding
Zhaoyang Li, Cheng Lu, Xiaolin Xu, Kaifei Zhang, Yujia Gu, Banghua Li, Yuan Zong, Wenming Zheng
Abstract
This paper introduces our solution, the Task-Specific Feature Learning (TSFL) method, designed to address the second track of the MEIJU Challenge at ICASSP 2025, namely, Imbalanced Emotion and Intent Recognition (English). The TSFL method incorporates three core components: the use of LLM features to represent multimodal signals, coarse-grained task-specific feature decomposition, and fine-grained task-specific feature learning. These components enable the effective joint learning of emotion-discriminative and intent-discriminative features. As a result, our method achieved a JRBM score of 0.6230, significantly outperforming the official baseline result and surpassing all other competing teams to win the championship.
BibTeX
@inproceedings{icassp2025_enhancingtaskspe,
title = {Enhancing Task-Specific Feature Learning with LLMs for Multimodal Emotion and Intent Joint Understanding},
author = {Zhaoyang Li and Cheng Lu and Xiaolin Xu and Kaifei Zhang and Yujia Gu and Banghua Li and Yuan Zong and Wenming Zheng},
booktitle = {ICASSP 2025},
year = {2025}
}