{"type":"ScholarlyArticle","title":"An Emotion-Preserving Conditional Information Bottleneck for Domain-Generalizable Speech Emotion Recognition","authors":[{"name":"Zhichen Yuan","slug":"zhichen-yuan","given":"Zhichen","family":"Yuan","affiliation":""},{"name":"C. L. Philip Chen","slug":"c-l-philip-chen","given":"C. L. Philip","family":"Chen","affiliation":""},{"name":"Shuzhen Li","slug":"shuzhen-li","given":"Shuzhen","family":"Li","affiliation":""},{"name":"Tong Zhang","slug":"tong-zhang","given":"Tong","family":"Zhang","affiliation":""}],"abstract":"Domain-generalizable speech emotion recognition (DG-SER) aims to ensure the robustness of SER models across unknown domains, which is essential for real-world human-machine interaction systems. Most DG-SER approaches employ alignment or adversarial strategies with domain labels to promote generalization. However, these strategies often confine generalization to predefined domains, limiting robustness under diverse real-world speech variations. To address these challenges, this paper proposes an emotion-preserving conditional information bottleneck framework (EP-CIB) for domain-free DG-SER. Specifically, EP-CIB introduces a nuisance proxy representation learning module to learn a nuisance proxy as the broad non-emotional variability without requiring any domain annotations, covering both defined and previously unseen domains. It then extracts coarse-grained emotion features via the consistency-aware emotion representation learning module. EP-CIB further introduces an emotion-preserving conditional information bottleneck that, conditioned on the emotion label, disentangles the nuisance proxy from the coarse-grained emotion representation, improving domain-free generalization under open-ended domain shifts. EP-CIB departs from implicit domain surrogates in prior domain-free methods by explicitly learning a proxy for nuisance domains and disentangling it from emotion features, enabling domain-free emotion representation learning. The state-of-the-art performance in both speaker-independent and cross-corpus settings, including an 18% improvement on EmoDB-to-CASIA transfer, demonstrates the effectiveness of EP-CIB for DG-SER.","doi":"10.24963/ijcai.2026/414","url":"https://ijcai.org/proceedings/2026/414","pdf":"https://ijcai.org/proceedings/2026/0414.pdf","markdown":"https://ijcai.org/proceedings/2026/414.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/414","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Humans and AI","track":"Main Track","number":414,"pages":{"first":3719,"last":3727},"keywords":["Humans and AI: Human-computer interaction","Natural Language Processing: Speech","Natural Language Processing: Sentiment analysis, stylistic analysis, and argument mining","Machine Learning: Robustness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}