Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity
Abstract In recent years, the adoption of deep learning techniques has allowed to obtain major breakthroughs in the automatic music generation research field, sparking a renewed interest in generative music. A great deal of work has focused on the possibility of conditioning the generation process i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-05-01
|
| Series: | EURASIP Journal on Audio, Speech, and Music Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13636-023-00288-5 |
| _version_ | 1797822731447697408 |
|---|---|
| author | Luca Comanducci Davide Gioiosa Massimiliano Zanoni Fabio Antonacci Augusto Sarti |
| author_facet | Luca Comanducci Davide Gioiosa Massimiliano Zanoni Fabio Antonacci Augusto Sarti |
| author_sort | Luca Comanducci |
| collection | DOAJ |
| description | Abstract In recent years, the adoption of deep learning techniques has allowed to obtain major breakthroughs in the automatic music generation research field, sparking a renewed interest in generative music. A great deal of work has focused on the possibility of conditioning the generation process in order to be able to create music according to human-understandable parameters. In this paper, we propose a technique for generating chord progressions conditioned on harmonic complexity, as grounded in the Western music theory. More specifically, we consider a pre-existing dataset annotated with the related complexity values and we train two variations of Variational Autoencoders (VAE), namely a Conditional-VAE (CVAE) and a Regressor-based VAE (RVAE), in order to condition the latent space depending on the complexity. Through a listening test, we analyze the effectiveness of the proposed techniques. |
| first_indexed | 2024-03-13T10:13:29Z |
| format | Article |
| id | doaj.art-4dd43aac6fa4491c89fefea081885cff |
| institution | Directory Open Access Journal |
| issn | 1687-4722 |
| language | English |
| last_indexed | 2024-03-13T10:13:29Z |
| publishDate | 2023-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Audio, Speech, and Music Processing |
| spelling | doaj.art-4dd43aac6fa4491c89fefea081885cff2023-05-21T11:22:38ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47222023-05-012023111710.1186/s13636-023-00288-5Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexityLuca Comanducci0Davide Gioiosa1Massimiliano Zanoni2Fabio Antonacci3Augusto Sarti4Dipartimento di Elettronica, Infomazione e Bioignegneria (DEIB), Politecnico di MilanoDipartimento di Elettronica, Infomazione e Bioignegneria (DEIB), Politecnico di MilanoDipartimento di Elettronica, Infomazione e Bioignegneria (DEIB), Politecnico di MilanoDipartimento di Elettronica, Infomazione e Bioignegneria (DEIB), Politecnico di MilanoDipartimento di Elettronica, Infomazione e Bioignegneria (DEIB), Politecnico di MilanoAbstract In recent years, the adoption of deep learning techniques has allowed to obtain major breakthroughs in the automatic music generation research field, sparking a renewed interest in generative music. A great deal of work has focused on the possibility of conditioning the generation process in order to be able to create music according to human-understandable parameters. In this paper, we propose a technique for generating chord progressions conditioned on harmonic complexity, as grounded in the Western music theory. More specifically, we consider a pre-existing dataset annotated with the related complexity values and we train two variations of Variational Autoencoders (VAE), namely a Conditional-VAE (CVAE) and a Regressor-based VAE (RVAE), in order to condition the latent space depending on the complexity. Through a listening test, we analyze the effectiveness of the proposed techniques.https://doi.org/10.1186/s13636-023-00288-5Conditional music generationDeep learningVAEHarmonic complexity |
| spellingShingle | Luca Comanducci Davide Gioiosa Massimiliano Zanoni Fabio Antonacci Augusto Sarti Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity EURASIP Journal on Audio, Speech, and Music Processing Conditional music generation Deep learning VAE Harmonic complexity |
| title | Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity |
| title_full | Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity |
| title_fullStr | Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity |
| title_full_unstemmed | Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity |
| title_short | Variational Autoencoders for chord sequence generation conditioned on Western harmonic music complexity |
| title_sort | variational autoencoders for chord sequence generation conditioned on western harmonic music complexity |
| topic | Conditional music generation Deep learning VAE Harmonic complexity |
| url | https://doi.org/10.1186/s13636-023-00288-5 |
| work_keys_str_mv | AT lucacomanducci variationalautoencodersforchordsequencegenerationconditionedonwesternharmonicmusiccomplexity AT davidegioiosa variationalautoencodersforchordsequencegenerationconditionedonwesternharmonicmusiccomplexity AT massimilianozanoni variationalautoencodersforchordsequencegenerationconditionedonwesternharmonicmusiccomplexity AT fabioantonacci variationalautoencodersforchordsequencegenerationconditionedonwesternharmonicmusiccomplexity AT augustosarti variationalautoencodersforchordsequencegenerationconditionedonwesternharmonicmusiccomplexity |