3 papers
eess.AS2026
MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
Dohwan Kim, Jung-Woo Choi
While discriminative models for multi-channel speech separation excel in reference-based metrics, they often exhibit suboptimal human listening quality. To address this, we propose…
cs.SD2026
DISPATCH: Distilling Selective Patches for Speech Enhancement
Dohwan Kim, Jung-Woo Choi
In speech enhancement, knowledge distillation (KD) compresses models by transferring a high-capacity teacher's knowledge to a compact student. However, conventional KD methods trai…
eess.AS2025
Self-Guided Target Sound Extraction and Classification Through Universal Sound Separation Model and Multiple Clues
Younghoo Kwon, Dongheon Lee, Dohwan Kim +1
This paper introduces a multi-stage self-directed framework designed to address the spatial semantic segmentation of sound scene (S5) task in the DCASE 2025 Task 4 challenge. This…