Automatic Music Generation Using Machine Learning

Cosma, Oliver-Grigorie; Domuta, Claudiu; Gota, Dan; Stan, Ovidiu; Fanca, Alexandra; Pop, Adela; Valean, Honoriu; Miclea, Liviu

doi:10.1109/icecet58911.2023.10389273

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The subsequent integration of GNNs into the MIDI-based framework amplifies this transformative journey. GNNs showcase an impressive capacity to generate diverse and innovative content across various domains and hold the potential to revolutionize the essence of music production [23]- [27]. By synthesizing the expressive roots of traditional music composition with cutting-edge technology, the amalgamation of GNNs with MIDI technologies stands at the forefront of reshaping the landscape of music creation.…”

Section: Introductionmentioning

confidence: 99%

MIDI-based generative neural networks with variational autoencoders for innovative music creation

Rosalina,

Sahuri

2024

IJAAS

View full text Add to dashboard Cite

By utilizing variational autoencoder (VAE) architectures in musical instrument digital interface (MIDI)-based generative neural networks (GNNs), this study explores the field of creative music composition. The study evaluates the success of VAEs in generating musical compositions that exhibit both structural integrity and a resemblance to authentic music. Despite achieving convergence in the latent space, the degree of convergence falls slightly short of initial expectations. This prompts an exploration of contributing factors, with a particular focus on the influence of training data variation. The study acknowledges the optimal performance of VAEs when exposed to diverse training data, emphasizing the importance of sufficient intermediate data between extreme ends. The intricacies of latent space dimensions also come under scrutiny, with challenges arising in creating a smaller latent space due to the complexities of representing data in N dimensions. The neural network tends to position data further apart, and incorporating additional information necessitates exponentially more data. Despite the suboptimal parameters employed in the creation and training process, the study concludes that they are sufficient to yield commendable results, showcasing the promising potential of MIDI-based GNNs with VAEs in pushing the boundaries of innovative music composition.

show abstract

Section: Introductionmentioning

confidence: 99%