PitchIn, audio-language models for natural-language vocal coaching, and the PeerCoach Dataset are introduced: 14,445 instruction examples covering Focused QA, Overall Feedback, and Recognition QA and significantly preferred for usefulness.
Hayeon Bang, Hounsu Kim, Joonyong Park et al.· 0 citations
Unlike autoregressive models, discrete diffusion-based models for zero-shot text-to-speech generate speech tokens in parallel and can revisit earlier predictions. Mask-and-replace training extends mask-only training by randomly replacing some tokens, and its gains are commonly attributed to self-correction, the ability...
Hounsu Kim, Joonyong Park, Yuki Saito et al.· 0 citations
VocalCoachBench is introduced, a benchmark for evaluating audio-language models on expert vocal coaching feedback for singing, moving audio-language evaluation beyond description toward analytic feedback.
Hayeon Bang, Hounsu Kim, Wonil Kim et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.