CONLON: A pseudo-song generator based on a new pianoroll, Wasserstein autoencoders, and optimal interpolations

Luca Angioloni, V.A.J. (Tijn) Borghuis, Lorenzo Brusci, Paolo Frasconi

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

44 Downloads (Pure)

Abstract

We introduce CONLON, a pattern-based MIDI generation method that employs a new lossless pianoroll-like data description in which velocities and durations are stored in separate channels. CONLON uses Wasserstein autoencoders as the underlying generative model. Its generation strategy is similar to interpolation, where MIDI pseudo-songs are obtained by concatenating patterns decoded from smooth trajectories in the embedding space, but aims to produce a smooth result in the pattern space by computing optimal trajectories as the solution of a widest-path problem. A set of surveys enrolling 69 professional musicians shows that our system, when trained on datasets of carefully selected and coherent patterns, is able to produce pseudo-songs that are musically consistent and potentially useful for professional musicians. Additional materials can be found at https://paolo-f.github.io/CONLON/ .
Original languageEnglish
Title of host publicationProceedings of the 21st International Society for Music Information Retrieval Conference
EditorsJulie Cummings, Jin Ha Lee, Brian McFee, Markus Schedl, Johanna Devaney, Corey McKay, Eva Zangerle, Timothy de Reuse
PublisherInternational Society for Music Information Retrieval
Pages876-883
Publication statusPublished - Oct 2020
Event21st International Society for Music Information Retrieval (virtual) -
Duration: 11 Oct 202016 Oct 2020

Conference

Conference21st International Society for Music Information Retrieval (virtual)
Period11/10/2016/10/20

Keywords

  • Machine learning
  • Music generation
  • Wasserstein autoencoders
  • Pianoroll representation
  • Interpolation

Fingerprint

Dive into the research topics of 'CONLON: A pseudo-song generator based on a new pianoroll, Wasserstein autoencoders, and optimal interpolations'. Together they form a unique fingerprint.

Cite this