2023/12/25 by Chengxin Chen, Chen, Chengxin, Pengyuan Zhang +1 · 1 citation
Computer Science · Psychology · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Emotion and Mood Recognition #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2312.15593
openalex publication_date 2023/12/25 · openalex created_date 2023/12/29 · openalex updated_date 2026/07/28
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.