## Frontmatter | | | | --- | --- | | Authors | [[Umut Güçlü]], [[Yağmur Güçlütürk]], [[Luca Ambrogioni]], [[Eric Maris]], [[Rob van Lier]], [[Marcel van Gerven]] | | Date | 2017/12 | | Source | [[Conference on Neural Information Processing Systems Workshops]] | | URL | https://nips2017creativity.github.io/doc/WaveCRF.pdf | | Citation | Güçlü, U., Güçlütürk, Y., Ambrogioni, L., Maris, E., van Lier, R., & van Gerven, M. (2017). [[Algorithmic composition of polyphonic music with the WaveCRF]]. In _Conference on Neural Information Processing Systems Workshops_. [[URL](https://nips2017creativity.github.io/doc/WaveCRF.pdf)]. #Conference | ## Abstract Here, we propose a new approach for modeling conditional probability distributions of polyphonic music by combining WaveNET and CRF-RNN variants, and show that this approach beats LSTM and WaveNET baselines that do not take into account the statistical dependencies between simultaneous notes. ## PDF ![[Algorithmic composition of polyphonic music with the WaveCRF.pdf]]