Professional Summary
Sunchan Park is a Postdoctoral Researcher at Pusan National University. He has worked extensively on speech processing, including speech recognition, speaker recognition, and speech emotion recognition. Building on this foundation, he is expanding his research into multimodal AI, aiming to bridge speech, vision, and language for next-generation intelligent systems.
Education
PhD Electronics Engineering
Pusan National University
MS Electronics Engineering
Pusan National University
BS Electronics Engineering
Pusan National University
Interests
Multimodal AI
Audio-Visual Understanding
Representation Learning
Speech Processing
Recent Publications
“Compositional Agentic Formulation Search for Open-Vocabulary Audio-Visual Event Localization,”
ICML Workshop,
2026.
“Group-wise Layer Aggregation of Self-Supervised Representations for Speech Emotion Recognition,”
IEEE Signal Processing Letters (Accepted),
2026.
“Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker Embedding,”
IEEE Access,
vol. 13,
pp. 45473-45487,
2025.
“Reverberant Environment Embedding using Dereverberation Autoencoder,”
Electronics Letters,
vol. 61,
no. 1,
pp. e70134,
2025.