PianoKontext model generates expressive piano performances from MIDI

Researchers have developed PianoKontext, a novel flow matching model designed for expressive performance rendering in classical piano music. This model can generate variable-length performances by leveraging a pretrained Music2Latent model. PianoKontext synthesizes MIDI scores into deadpan audio and uses Dynamic Time Warping in the latent space to create training data, enabling it to learn dependencies between musical scores and expressive performances. AI

RANK_REASON The cluster contains a research paper detailing a new model for music generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Music2Latent
• PianoKontext

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →