Convolutional Generative Adversarial Network, via Transfer Learning, for Traditional Scottish Music Generation

Marchetti, Francesco; Wilson, Callum; Powell, Cheyenne; Minisci, Edmondo; Riccardi, Annalisa

doi:10.1007/978-3-030-72914-1_13

“…For intra-tracks metrics, the jamming model produces the best results; however, the composer model outperformed the other models for the inter-track metrics. MuseGAN architecture and variations are widely used in recent studies [26] [35].…”

Section: Symbolic Music Generation Using Ganmentioning

confidence: 99%

“…Marchetti et al [26] studied music generation for traditional Scottish music. The dataset is preprocessed to be similar to the BinaryMuseGAN [42].…”

Section: Symbolic Music Generation Using Ganmentioning

confidence: 99%

Difficulty Controlled Piano Music Generation using GAN Approach

Ghatas¹,

Fayek²,

Hadhoud³

2022

Preprint

View full text Add to dashboard Cite

<p>Musical learning is important whether for entertainment or as a profession. However, learning music depends on practice; finding a musical piece on the player’s level is challenging. This paper proposes a novel method for automated difficulty-controlled piano music generation using a Generative Adversarial Network (GAN) approach. Two applications are studied (1) Generation of a random musical piece given the required difficulty and (2) Generation of a musical piece similar (melodic similarity) to an input musical piece in the required difficulty. We use a Generative Adversarial Network for music generation and an autoencoder for encoding the melody of the input musical piece. The model is evaluated using multiple metrics for musicality, similarity, and difficulty. The results prove the effectiveness of the proposed approach and encourage future research in the same area.</p>

show abstract

“…For intra-tracks metrics, the jamming model produces the best results; however, the composer model outperformed the other models for the inter-track metrics. MuseGAN architecture and variations are widely used in recent studies [26] [35].…”

Section: Symbolic Music Generation Using Ganmentioning

confidence: 99%

“…Marchetti et al [26] studied music generation for traditional Scottish music. The dataset is preprocessed to be similar to the BinaryMuseGAN [42].…”

Section: Symbolic Music Generation Using Ganmentioning

confidence: 99%

Difficulty Controlled Piano Music Generation using GAN Approach

Ghatas¹,

Fayek²,

Hadhoud³

2022

Preprint

0

View full text Add to dashboard Cite

<p>Musical learning is important whether for entertainment or as a profession. However, learning music depends on practice; finding a musical piece on the player’s level is challenging. This paper proposes a novel method for automated difficulty-controlled piano music generation using a Generative Adversarial Network (GAN) approach. Two applications are studied (1) Generation of a random musical piece given the required difficulty and (2) Generation of a musical piece similar (melodic similarity) to an input musical piece in the required difficulty. We use a Generative Adversarial Network for music generation and an autoencoder for encoding the melody of the input musical piece. The model is evaluated using multiple metrics for musicality, similarity, and difficulty. The results prove the effectiveness of the proposed approach and encourage future research in the same area.</p>

show abstract

“…In many areas of music, arts, and design, artificial intelligence (AI) can procedurally generate new cultural artifacts [21,6,27,31,30]. With the recent developments of Generative Adversarial Networks (GANs), AI technology can become a powerful asset for human creators to design complex objects.…”

Section: Introductionmentioning

confidence: 99%

Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space

Grabe¹,

Zhu²,

Agirrezabal³

2022

Preprint

0

View full text Add to dashboard Cite

This paper presents a novel approach for guiding a Generative Adversarial Network trained on the FashionGen dataset to generate designs corresponding to target fashion styles. Finding the latent vectors in the generator's latent space that correspond to a style is approached as an evolutionary search problem. A Gaussian mixture model is applied to identify fashion styles based on the higher-layer representations of outfits in a clothing-specific attribute prediction model. Over generations, a genetic algorithm optimizes a population of designs to increase their probability of belonging to one of the Gaussian mixture components or styles. Showing that the developed system can generate images of maximum fitness visually resembling certain styles, our approach provides a promising direction to guide the search for style-coherent designs.

show abstract

Convolutional Generative Adversarial Network, via Transfer Learning, for Traditional Scottish Music Generation

Cited by 7 publications

References 19 publications

Difficulty Controlled Piano Music Generation using GAN Approach

Difficulty Controlled Piano Music Generation using GAN Approach

Difficulty Controlled Piano Music Generation using GAN Approach

Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space

Contact Info

Product

Resources

About