A codec language model adapted from VALLE synthesizes expressive piano audio from performance MIDI, beating the M2A baseline on objective and subjective tests.
In addition, Piano-Encodec achieves high-fidelity reconstruction of human performances, with much lower FAD, spectrogram, and chroma distortions than generative models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling
A codec language model adapted from VALLE synthesizes expressive piano audio from performance MIDI, beating the M2A baseline on objective and subjective tests.