3 papers
cs.SD2026
SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion
Hounsu Kim, Juhan Nam
Speaker-decoupled speech codecs can reduce bitrate by separating global speaker attributes from local content and prosody, while supporting voice conversion. Existing speaker-decou…
cs.SD2026
D3PIA: A Discrete Denoising Diffusion Model for Piano Accompaniment Generation From Lead sheet
Eunjin Choi, Hounsu Kim, Hayeon Bang +2
Generating piano accompaniments in the symbolic music domain is a challenging task that requires producing a complete piece of piano music from given melody and chord constraints,…
cs.SD2025
D3RM: A Discrete Denoising Diffusion Refinement Model for Piano Transcription
Hounsu Kim, Taegyun Kwon, Juhan Nam
Diffusion models have been widely used in the generative domain due to their convincing performance in modeling complex data distributions. Moreover, they have shown competitive re…