Eujin Kim — accepted AI-conference papers

2026

BEAT2AASIST MODEL WITH LAYER FUSION FOR ESDD 2026 CHALLENGE

Sanghyeok Chung, Eujin Kim, Donggun Kim, Gaeun Heo, Jeongbin You, Nahyun Lee +4

ICASSP 2026poster

Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale benchmark for Environmental Sound Deepfake Detection (ESDD). We propose BEAT2AASIST which extends BEATs-AASIST by splitting BEATs-der…

Cited by 3 Source ↗PDF ↗Scholar ↗

2026

BEAT2AASIST: BEATs Feature Splitting with Dual-Branch AASIST for Environmental Sound Deepfake Detection

Sanghyeok ‍Chung, Seungsang Oh, Donggun Kim, Jeongbin You, Il-Youp Kwak, Gaeun Heo +4

IJCAI 2026

Recent advances in text-to-audio (TTA) and audio-to-audio (ATA) generation models have enabled the creation of highly realistic environmental sounds, raising growing concerns about malicious audio manipulation in real-world scenarios. To address this emerging threat, the ESDD 2026 Challenge was intr

Cited by 0 Scholar ↗