Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset

ICLR 2019 Curtis HawthorneAndriy StasyukAdam RobertsIan SimonCheng-Zhi Anna HuangSander DielemanErich ElsenJesse EngelDouglas Eck

Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales. Fortunately, most music is also highly structured and can be represented as discrete note events played on musical instruments... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.