以更少资源学习更多：面向低资源语音情感识别的自监督方法
Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition
AI总结：
本文研究低资源语音情感识别，采用对比学习和BYOL自监督方法提升跨语言泛化，在乌尔都语、德语和孟加拉语上F1分别提升10.6%、15.2%和13.9%，为低资源语言情感识别系统提供基础。
摘要：
语音情感识别（SER）在深度学习的推动下已取得显著进展，但由于标注数据稀缺，在低资源语言（LRLs）中仍然具有挑战性。在本工作中，我们探索无监督学习以改善低资源环境下的SER。具体而言，我们研究对比学习（CL）和Bootstrap Your Own Latent（BYOL）作为自监督方法，以增强跨语言泛化能力。我们的方法取得了显著的F1分数提升：乌尔都语提升10.6%，德语提升15.2%，孟加拉语提升13.9%，证明了它们在低资源语言中的有效性。此外，我们分析模型行为，以提供关于影响跨语言性能的关键因素的见解，同时指出低资源SER中的挑战。本工作为面向代表性不足语言开发更具包容性、可解释性和鲁棒性的情感识别系统奠定了基础。
英文摘要：
Speech Emotion Recognition (SER) has seen significant progress with deep learning, yet remains challenging for Low-Resource Languages (LRLs) due to the scarcity of annotated data. In this work, we explore unsupervised learning to improve SER in low-resource settings. Specifically, we investigate contrastive learning (CL) and Bootstrap Your Own Latent (BYOL) as self-supervised approaches to enhance cross-lingual generalization. Our methods achieve notable F1 score improvements of 10.6% in Urdu, 15.2% in German, and 13.9% in Bangla, demonstrating their effectiveness in LRLs. Additionally, we analyze model behavior to provide insights on key factors influencing performance across languages, and also highlighting challenges in low-resource SER. This work provides a foundation for developing more inclusive, explainable, and robust emotion recognition systems for underrepresented languages.
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。
