Convolutional Generative Adversarial Network, via Transfer Learning, for traditional Scottish music generation

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

The concept of a Binary Multi-track Sequential Generative Adversarial Network (BinaryMuseGAN) used for the generation of music has been applied and tested for various types of music. However, the concept is yet to be tested on more specific genres of music such as traditional Scottish music, for which extensive collections are not readily available. Hence exploring the capabilities of a Transfer Learning (TL) approach on these types of music is an interesting challenge for the methodology. The curated set of MIDI Scottish melodies was preprocessed in order to obtain the same number of tracks used in the BinaryMuseGAN model; converted into pianoroll format and then used as training set to fine tune a pretrained model, generated from the Lakh MIDI dataset. The results obtained have been compared with the results obtained by training the same GAN model from scratch on the sole Scottish music dataset. Results are presented in terms of variation and average performances achieved at different epochs for five performance metrics, three adopted from the Lakh dataset (qualified note rate, polyphonicity, tonal distance) and two custom defined to highlight Scottish music characteristics (dotted rhythm and pentatonic note). From these results, the TL method shows to be more effective, with lower number of epochs, to converge stably and closely to the original dataset reference metrics values.
Original languageEnglish
Title of host publicationArtificial Intelligence in Music, Sound, Art and Design
Subtitle of host publication10th International Conference, EvoMUSART 2021, Held as Part of EvoStar 2021, Virtual Event, April 7–9, 2021, Proceedings
EditorsJuan Romero, Tiago Martins, Nereida Rodríguez-Fernández
Place of PublicationCha, Switzerland
PublisherSpringer
Number of pages16
Volume12693
ISBN (Electronic)978-3-030-72914-1
ISBN (Print)978-3-030-72913-4
Publication statusPublished - 17 May 2021
Event10th International Conference on Artificial Intelligence in Music, Sound, Art and Design - Virtual, Seville, Spain
Duration: 7 Apr 20219 Apr 2021
http://www.evostar.org/2021/evomusart/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer

Conference

Conference10th International Conference on Artificial Intelligence in Music, Sound, Art and Design
Abbreviated titleEvoMUSART
CountrySpain
CitySeville
Period7/04/219/04/21
Internet address

Keywords

  • Generative Adversarial Network
  • Transfer Learning
  • convolutional neural network
  • Scottish music

Cite this