Interpretable Singing Emotion Recognition Using Acoustic and Vocal Technique Features
This paper proposes an interpretable framework for singing emotion recognition using singing-specific descriptors.
This paper introduces a novel approach to singing emotion recognition by using singing-specific descriptors and interpretable methods.
Before reading this…
Applications
- →music analysis
- →music recommendation
To understand this paper, make sure you know these concepts first:
- deep learning modelsfind papers →
- singing voice analysisfind papers →
Abstract
More Like ThisSinging emotion recognition relies predominantly on deep learning models that achieve strong performance but offer limited insight into the vocal characteristics driving emotion, of- ten overlooking the singing voice as a distinct signal. We propose an interpretable singing emotion recognition framework using a compact set of singing-specific descriptors across prosody, spec- tral features, phonetics, and vocal technique. To decode model decisions and link predictions to measurable acoustic phenomena, we employ SHAP and apply GRAD-CAM to qualitatively assess the learned representations of vocal techniques. Evaluations show that singing-specific features reduce cross-singer variability, while vocal technique descriptors provide interpretable insights into singing expression. Furthermore, out-of-domain evaluation on VocalSet reveals interesting associations between emotional expression and ground-truth technical execution. The analysis highlights vibrato and pharyngeal techniques as salient cues of emotional delivery, with SHAP indicating that vibrato is context-dependent on articulation rate. These findings emphasize the value of domain-specific features for interpretable singing emotion analysis.