@inproceedings{b0831245a9954691a578587b33130e76,
title = "Many-to-many symbolic multi-track music genre transfer",
abstract = "This paper shows the feasibility of a variant of the Generative Adversarial Network (GAN), called Star GAN, for music genre transfer. This method is noteworthy in that it simultaneously learns many-to-many mappings across different attribute domains using a single generator network. A similar architecture to research in MuseGAN and CycleGAN is applied. Also, as in MGTGAN, Desert Camel MIDI dataset is use for training and testing.",
keywords = "CNN, Deep Learning, Genre, MIDI, Music, StarGAN, Style, Transfer",
author = "Michel Pezzat and Hector Perez-Meana and Toru Nakashika and Mariko Nakano",
note = "Publisher Copyright: {\textcopyright} 2020 The authors and IOS Press. All rights reserved.; 19th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2020 ; Conference date: 22-09-2020 Through 24-09-2020",
year = "2020",
month = sep,
day = "15",
doi = "10.3233/FAIA200572",
language = "Ingl{\'e}s",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press BV",
pages = "272--281",
editor = "Hamido Fujita and Ali Selamat and Sigeru Omatu",
booktitle = "Knowledge Innovation Through Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 19th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2020",
}