EmoFedProto: Privacy-Preserving Vietnamese Speech Emotion Recognition via Prototype-Based Federated Learning
EAI Endorsed Transactions on AI and Robotics · 23.04.2026 · 5
DOI: 10.4108/airo.11595 ↗Kurz gefasst
Fachartikel in der Zeitschrift EAI Endorsed Transactions on AI and Robotics, online erschienen am 23.04.2026. Verfasst von Quang-Anh Nguyen-Duc und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Speech Emotion Recognition (SER) plays a fundamental role in affective computing by enabling machines to infer human emotional states from vocal expressions. However, most existing SER systems rely on centralized training paradigms, which raise serious privacy concerns due to the sensitive nature of speech data. Federated Learning (FL) offers a privacy-preserving alternative by allowing collaborative model training without sharing raw data, yet its performance often degrades significantly under non-IID data distributions, a common characteristic of speech emotion datasets caused by speaker variability and emotion imbalance. To address these challenges, we propose EmoFedProto, a prototype-based federated learning framework with clustering-enhanced prototype aggregation tailored for Vietnamese speech emotion recognition in low-resource settings. Instead of exchanging full model parameters, EmoFedProto communicates class-level feature prototypes, enabling more robust alignment across heterogeneous clients. Experiments conducted on the VNEMOS dataset under realistic non-IID and few-shot conditions demonstrate that EmoFedProto achieves an accuracy of 0.875, outperforming the baseline FedProto (0.825), while reducing performance variability by 44%. These results indicate that clustering-based prototype federated learning is an effective and communication-efficient solution for privacy-preserving speech emotion recognition, particularly in low-resource languages and realworld federated environments.
Zitieren
APA
Nguyen-Duc, Q., Pham, D. M., Kim, T. D., Pham, T. P., Nguyen, M., Le, X., & Nguyen, V. (2026). EmoFedProto: Privacy-Preserving Vietnamese Speech Emotion Recognition via Prototype-Based Federated Learning. EAI Endorsed Transactions on AI and Robotics, 5. https://doi.org/10.4108/airo.11595
Vancouver
Nguyen-Duc Q, Pham DM, Kim TD, Pham TP, Nguyen M, Le X, et al. EmoFedProto: Privacy-Preserving Vietnamese Speech Emotion Recognition via Prototype-Based Federated Learning. EAI Endorsed Transactions on AI and Robotics. 2026;5. doi:10.4108/airo.11595
BibTeX
@article{NguyenDuc2026,
author = {Nguyen-Duc, Quang-Anh and Pham, Duc Minh and Kim, Thai Dinh and Pham, Thao Phuong and Nguyen, Minh-Anh and Le, Xuan-Hai and Nguyen, Van-Ninh},
title = {EmoFedProto: Privacy-Preserving Vietnamese Speech Emotion Recognition via Prototype-Based Federated Learning},
journal = {EAI Endorsed Transactions on AI and Robotics},
year = {2026},
volume = {5},
doi = {10.4108/airo.11595}
}
EUVIMED