English

DSNet: Disentangled Siamese Network with Neutral Calibration for Speech Emotion Recognition

Sound 2023-12-27 v1 Artificial Intelligence Audio and Speech Processing

Abstract

One persistent challenge in deep learning based speech emotion recognition (SER) is the unconscious encoding of emotion-irrelevant factors (e.g., speaker or phonetic variability), which limits the generalization of SER in practical use. In this paper, we propose DSNet, a Disentangled Siamese Network with neutral calibration, to meet the demand for a more robust and explainable SER model. Specifically, we introduce an orthogonal feature disentanglement module to explicitly project the high-level representation into two distinct subspaces. Later, we propose a novel neutral calibration mechanism to encourage one subspace to capture sufficient emotion-irrelevant information. In this way, the other one can better isolate and emphasize the emotion-relevant information within speech signals. Experimental results on two popular benchmark datasets demonstrate the superiority of DSNet over various state-of-the-art methods for speaker-independent SER.

Keywords

Cite

@article{arxiv.2312.15593,
  title  = {DSNet: Disentangled Siamese Network with Neutral Calibration for Speech Emotion Recognition},
  author = {Chengxin Chen and Pengyuan Zhang},
  journal= {arXiv preprint arXiv:2312.15593},
  year   = {2023}
}

Comments

15 pages, 4 figures

R2 v1 2026-06-28T14:01:12.803Z