ISMIR

Codified Audio Language Modeling Learns Useful Representations for Music Information Retrieval
We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for …
Rodrigo Castellon, Chris Donahue, Percy Liang
arXiv PDF BibTeX Code
Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music
Modern keyboards allow a musician to play multiple instruments at the same time by assigning zones – fixed pitch ranges of the …
Hao-Wen Dong, Chris Donahue, Taylor Berg-Kirkpatrick, Julian McAuley
arXiv PDF BibTeX 🔊 Examples Code
LakhNES: Improving Multi-instrumental Music Generation with Cross-domain Pre-training
We are interested in the task of generating multi-instrumental music scores. The Transformer architecture has recently shown great …
Chris Donahue, Huanru Henry Mao, Yiting Ethan Li, Garrison W. Cottrell, Julian McAuley
arXiv PDF BibTeX 🔊 Examples Code
The NES Music Database: A Multi-instrumental Dataset with Expressive Performance Attributes
Existing research on music generation focuses on composition, but often ignores the expressive performance characteristics required for …
Chris Donahue, Huanru Henry Mao, Julian McAuley
arXiv PDF BibTeX Code Dataset Notebook