arXiv cs.AI· Fotini Kiriakopoulou, Vassilis Lyberatos, Spyridon Kantarelis, Athanasios Voulodimos, Giorgos Stamou·· 12 小时前AI 评分18
基于声学与声乐技巧特征的可解释歌唱情感识别
Interpretable Singing Emotion Recognition Using Acoustic and Vocal Technique Features
AI 导读
研究提出一个可解释的歌唱情感识别框架，用涵盖韵律、频谱、语音学和声乐技巧的紧凑特征集替代纯深度学习模型，并结合 SHAP 与 GRAD-CAM 将预测关联到可测量的声学现象。评估显示歌唱专用特征可降低跨歌手差异，声乐技巧描述符提供可解释的演唱表达洞察。在 VocalSet 上的域外评估发现颤音与咽音技巧是情感传达的显著线索，SHAP 表明颤音对咬字速率具有上下文依赖性。
正文 · 原文
Abstract:Singing 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.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32629 [cs.SD] |
| (or arXiv:2610.32629v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32629 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fotini Kiriakopoulou [view email]
[v1]
Fri, 23 Oct 2026 13:42:34 UTC (1,074 KB)
来源：arXiv cs.AI · arxiv.org