This paper explores the use of the Masked Autoregressive Flow (MAF) model for music generation, specifically addressing its limitation to univariate time series. To extend MAF for polyphonic melodies, three approaches are proposed and tested on the Lakh Pianoroll Dataset. The results show promising accuracy and the model’s ability to generate original, pleasing melodies, demonstrating the potential of this innovative interdisciplinary approach.
Generate Polyphonic Music with Multivariate Masked Autoregressive Flow / Daniele Castellana; Massimiliano Sirgiovanni. - ELETTRONICO. - (2025), pp. 503-508. ( European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)).
Generate Polyphonic Music with Multivariate Masked Autoregressive Flow
Daniele Castellana
Conceptualization
;
2025
Abstract
This paper explores the use of the Masked Autoregressive Flow (MAF) model for music generation, specifically addressing its limitation to univariate time series. To extend MAF for polyphonic melodies, three approaches are proposed and tested on the Lakh Pianoroll Dataset. The results show promising accuracy and the model’s ability to generate original, pleasing melodies, demonstrating the potential of this innovative interdisciplinary approach.
| File | Dimensione | Formato | |
|---|---|---|---|
|
ES2025-86.pdf
accesso aperto
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Open Access
Dimensione
1.57 MB
Formato
Adobe PDF
|
1.57 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
