3 papers
cs.SD2026
Gugak-VocalSet: A Multi-Genre Studio-Quality Dataset of Korean Traditional Singing with Sigimsae Annotations
Danbinaerin Han, Wonil Kim, Seah Hong +5
We present Gugak-VocalSet, the first publicly available audio dataset for Korean traditional singing with dense annotations of sigimsae, a structured pitch contour system of vocal…
cs.SD2026
Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation
Taejun Kim, Wonil Kim, Jongmin Jung +10
How can we verify whose music contributed to an AI-generated output? This paper demonstrates how input-based attribution can provide verifiable evidence of which audio sources were…
cs.IR2025
From Generation to Attribution: Music AI Agent Architectures for the Post-Streaming Era
Wonil Kim, Hyeongseok Wi, Seungsoon Park +12
Generative AI is reshaping music creation, but its rapid growth exposes structural gaps in attribution, rights management, and economic models. Unlike past media shifts, from live…