Group-wise Layer Aggregation of Self-Supervised Representations for Speech Emotion RecognitionJun 23, 2026·Sunchan Park,Hyung Soon Kim,Kyeongbo Kong· 0 min readTypeJournal articlePublicationIEEE Signal Processing Letters (Accepted)Last updated on Jun 23, 2026Source Themes AuthorsSunchan Park (he/him)Postdoctoral Researcher ← Compositional Agentic Formulation Search for Open-Vocabulary Audio-Visual Event Localization Jul 11, 2026Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker Embedding Mar 11, 2025 →
,,·
0 min read