MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions

@misc{katsamanis2025medusamultimodaldeep,
      title={MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions},
      author={Athanasios Katsamanis and Vassilis Katsouros and Efthymios Georgiou and Alexandros Potamianos and Georgios Chatzichristodoulou and Despoina Kosmopoulou and Antonios Kritikos and Anastasia Poulopoulou},
      year={2025},
      eprint={2506.09556},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.09556},
}