Samenvatting
We demonstrate a pattern-based MIDI music generation system with a generation strategy based on Wasserstein autoencoders and a novel variant of pianoroll descriptions of patterns which employs separate channels for note velocities and note durations and can be fed into classic DCGAN-style convolutional architectures. We trained the system on two new datasets (in the acid-jazz and high-pop genres) composed by musicians in our team with music generation in mind. Our demonstration shows that moving smoothly in the latent space allows us to generate meaningful sequences of four-bars patterns.
Originele taal-2 | Engels |
---|---|
Titel | Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020 |
Redacteuren | Christian Bessiere |
Uitgeverij | International Joint Conferences on Artificial Intelligence (IJCAI) |
Pagina's | 5225-5227 |
Aantal pagina's | 3 |
ISBN van elektronische versie | 9780999241165 |
DOI's | |
Status | Gepubliceerd - jul. 2020 |
Evenement | 29th International Joint Conference on Artificial Intelligence - 17th Pacific Rim International Conference on Artificial Intelligence, IJCAI 2020, PRICAI 2020 - Pacifico Convention Plaza Yokohama, Yokohama, Japan Duur: 11 jul. 2020 → 17 jul. 2020 Congresnummer: 29 https://ijcai20.org/ |
Congres
Congres | 29th International Joint Conference on Artificial Intelligence - 17th Pacific Rim International Conference on Artificial Intelligence, IJCAI 2020, PRICAI 2020 |
---|---|
Verkorte titel | IJCAI-PRICAI 2020 |
Land/Regio | Japan |
Stad | Yokohama |
Periode | 11/07/20 → 17/07/20 |
Internet adres |