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.

Pattern-Based Music Generation with Wasserstein Autoencoders and PRC Descriptions / Valentijn Borghuis, Luca Angioloni, Lorenzo Brusci, Paolo Frasconi. - ELETTRONICO. - (2020), pp. 5225-5227. (Intervento presentato al convegno Twenty-Ninth International Joint Conference on Artificial Intelligence) [10.24963/ijcai.2020/751].

Pattern-Based Music Generation with Wasserstein Autoencoders and PRC Descriptions

Luca Angioloni
;
Paolo Frasconi
2020

Abstract

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.
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Twenty-Ninth International Joint Conference on Artificial Intelligence
Goal 17: Partnerships for the goals
Valentijn Borghuis, Luca Angioloni, Lorenzo Brusci, Paolo Frasconi
File in questo prodotto:
File Dimensione Formato  
0751.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 91.79 kB
Formato Adobe PDF
91.79 kB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1214704
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact