arXiv 2604.074172026-04-08cs.SDeess.AS

语义-情感共鸣嵌入：一种跨语言语音情感识别的半监督范式

Semantic-Emotional Resonance Embedding: A Semi-Supervised Paradigm for Cross-Lingual Speech Emotion Recognition

School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Pengcheng Laboratory Xinjiang Network Node（鹏城实验室新疆网络节点）；Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术研究中心）；Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学具身智能联合研究实验室）；Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University（新疆大学丝绸之路多语言认知计算国际联合研究实验室）

Ya Zhao, Yinfeng Yu, Liejun Wang

备注：: Main paper (6 pages). Accepted for publication by IEEE International conference on Multimedia and Expo 2026 (ICME 2026)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于语义-情感共鸣嵌入的半监督框架，通过少量标注样本构建情感-语义结构，利用瞬时共鸣场实现无标注样本自组织，设计三重共鸣交互链损失提升标注与无标注样本间的交互能力，实验显示在多种语言上仅需5次标注即可达到高性能。

摘要：

跨语言语音情感识别（CLSER）旨在识别未见语言中的情感状态。然而，现有方法依赖于完整标签的语义同步和静态特征稳定性，阻碍了低资源语言达到高资源性能。为此，我们提出基于语义-情感共鸣嵌入（SERE）的半监督框架，这是一种无需目标语言标签或翻译对齐的跨语言动态特征范式。具体而言，SERE通过少量标注样本构建情感-语义结构。它通过瞬时共鸣场学习人类情感经验，使无标注样本自组织到该结构中，实现半监督语义指导和结构发现。此外，我们设计了三重共鸣交互链（TRIC）损失，以增强模型在情感高亮期间标注与无标注样本间的交互和嵌入能力。在多种语言上的广泛实验验证了本方法的有效性，仅需源语言中的5次标注即可。

英文摘要：

Cross-lingual Speech Emotion Recognition (CLSER) aims to identify emotional states in unseen languages. However, existing methods heavily rely on the semantic synchrony of complete labels and static feature stability, hindering low-resource languages from reaching high-resource performance. To address this, we propose a semi-supervised framework based on Semantic-Emotional Resonance Embedding (SERE), a cross-lingual dynamic feature paradigm that requires neither target language labels nor translation alignment. Specifically, SERE constructs an emotion-semantic structure using a small number of labeled samples. It learns human emotional experiences through an Instantaneous Resonance Field (IRF), enabling unlabeled samples to self-organize into this structure. This achieves semi-supervised semantic guidance and structural discovery. Additionally, we design a Triple-Resonance Interaction Chain (TRIC) loss to enable the model to reinforce the interaction and embedding capabilities between labeled and unlabeled samples during emotional highlights. Extensive experiments across multiple languages demonstrate the effectiveness of our method, requiring only 5-shot labeling in the source language.

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。