CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN
Abstract The two main research threads in computer-based music generation are the construction of autonomous music-making systems and the design of computer-based environments to assist musicians. In the symbolic domain, the key problem of automatically arranging a piece of music was extensively stu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-01-01
|
| Series: | Discover Artificial Intelligence |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44163-023-00047-7 |
| _version_ | 1797945826015707136 |
|---|---|
| author | Giorgio Barnabò Giovanni Trappolini Lorenzo Lastilla Cesare Campagnano Angela Fan Fabio Petroni Fabrizio Silvestri |
| author_facet | Giorgio Barnabò Giovanni Trappolini Lorenzo Lastilla Cesare Campagnano Angela Fan Fabio Petroni Fabrizio Silvestri |
| author_sort | Giorgio Barnabò |
| collection | DOAJ |
| description | Abstract The two main research threads in computer-based music generation are the construction of autonomous music-making systems and the design of computer-based environments to assist musicians. In the symbolic domain, the key problem of automatically arranging a piece of music was extensively studied, while relatively fewer systems tackled this challenge in the audio domain. In this contribution, we propose CycleDRUMS, a novel method for generating drums given a bass line. After converting the waveform of the bass into a mel-spectrogram, we can automatically generate original drums that follow the beat, sound credible, and be directly mixed with the input bass. We formulated this task as an unpaired image-to-image translation problem, and we addressed it with CycleGAN, a well-established unsupervised style transfer framework designed initially for treating images. The choice to deploy raw audio and mel-spectrograms enabled us to represent better how humans perceive music and to draw sounds for new arrangements from the vast collection of music recordings accumulated in the last century. In the absence of an objective way of evaluating the output of both generative adversarial networks and generative music systems, we further defined a possible metric for the proposed task, partially based on human (and expert) judgment. Finally, as a comparison, we replicated our results with Pix2Pix, a paired image-to-image translation network, and we showed that our approach outperforms it. |
| first_indexed | 2024-04-10T21:01:15Z |
| format | Article |
| id | doaj.art-acecec2a43f848c59d566aeb43052bbc |
| institution | Directory Open Access Journal |
| issn | 2731-0809 |
| language | English |
| last_indexed | 2024-04-10T21:01:15Z |
| publishDate | 2023-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Artificial Intelligence |
| spelling | doaj.art-acecec2a43f848c59d566aeb43052bbc2023-01-22T12:19:42ZengSpringerDiscover Artificial Intelligence2731-08092023-01-013111310.1007/s44163-023-00047-7CycleDRUMS: automatic drum arrangement for bass lines using CycleGANGiorgio Barnabò0Giovanni Trappolini1Lorenzo Lastilla2Cesare Campagnano3Angela Fan4Fabio Petroni5Fabrizio Silvestri6Department of Computer Engineering, Sapienza, University of RomeDepartment of Computer Engineering, Sapienza, University of RomeDepartment of Computer Engineering, Sapienza, University of RomeDepartment of Computer Science, Sapienza, University of RomeFAIR, METAFAIR, METADepartment of Computer Engineering, Sapienza, University of RomeAbstract The two main research threads in computer-based music generation are the construction of autonomous music-making systems and the design of computer-based environments to assist musicians. In the symbolic domain, the key problem of automatically arranging a piece of music was extensively studied, while relatively fewer systems tackled this challenge in the audio domain. In this contribution, we propose CycleDRUMS, a novel method for generating drums given a bass line. After converting the waveform of the bass into a mel-spectrogram, we can automatically generate original drums that follow the beat, sound credible, and be directly mixed with the input bass. We formulated this task as an unpaired image-to-image translation problem, and we addressed it with CycleGAN, a well-established unsupervised style transfer framework designed initially for treating images. The choice to deploy raw audio and mel-spectrograms enabled us to represent better how humans perceive music and to draw sounds for new arrangements from the vast collection of music recordings accumulated in the last century. In the absence of an objective way of evaluating the output of both generative adversarial networks and generative music systems, we further defined a possible metric for the proposed task, partially based on human (and expert) judgment. Finally, as a comparison, we replicated our results with Pix2Pix, a paired image-to-image translation network, and we showed that our approach outperforms it.https://doi.org/10.1007/s44163-023-00047-7Automatic music arrangementCycle-GANDeep learningSource separationAudio and speech processing |
| spellingShingle | Giorgio Barnabò Giovanni Trappolini Lorenzo Lastilla Cesare Campagnano Angela Fan Fabio Petroni Fabrizio Silvestri CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN Discover Artificial Intelligence Automatic music arrangement Cycle-GAN Deep learning Source separation Audio and speech processing |
| title | CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN |
| title_full | CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN |
| title_fullStr | CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN |
| title_full_unstemmed | CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN |
| title_short | CycleDRUMS: automatic drum arrangement for bass lines using CycleGAN |
| title_sort | cycledrums automatic drum arrangement for bass lines using cyclegan |
| topic | Automatic music arrangement Cycle-GAN Deep learning Source separation Audio and speech processing |
| url | https://doi.org/10.1007/s44163-023-00047-7 |
| work_keys_str_mv | AT giorgiobarnabo cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan AT giovannitrappolini cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan AT lorenzolastilla cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan AT cesarecampagnano cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan AT angelafan cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan AT fabiopetroni cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan AT fabriziosilvestri cycledrumsautomaticdrumarrangementforbasslinesusingcyclegan |