MuSeNet: Collaboration in the Music Artists Industry

Topîrceanu, Alexandru; Barina, Gabriel; Udrescu, Mihai

doi:10.1109/enic.2014.10

Cited by 18 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transformers have also been used to capture the long-term structure of music generation. MuseNet [11] uses a large-scale transformer model to predict the next token in the music sequence, and it is also able to take instrument and composer as input for music generation. Music Transformer [8] uses relative attention to focus on relational features which outperform the original transformer model.…”

Section: Related Work and Noveltymentioning

confidence: 99%

Everybody Compose: Deep Beats To Music

Shen,

Yao,

Liu

2023

Proceedings of the 14th ACM Multimedia Systems Conference

View full text Add to dashboard Cite

This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods -LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation -are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or "recoloring" beat sequences from existing works. CCS CONCEPTS• Applied computing → Sound and music computing; • Computing methodologies → Machine learning.

show abstract

Section: Related Work and Noveltymentioning

confidence: 99%

Everybody Compose: Deep Beats To Music

Shen,

Yao,

Liu

2023

Proceedings of the 14th ACM Multimedia Systems Conference

View full text Add to dashboard Cite

show abstract

“…Figure 18 shows the process of exploring parameters for generators and discriminators. The training cost is evaluated using the V(G, D) function as shown in Equation (6).…”

Section: Theory Analysis Of Ganmentioning

confidence: 99%

“…Sequence modeling was mainly driven by the 2 of 40 transformer [3], an attention-based module that eliminates circulatory or convolutional neural networks. Examples include Google's BERT (Bidirectional Encoder Representations from Transformers), GPT-3 (Generative Pretrained Transformer-3) for language modeling, Parallel WaveGAN for speech synthesis, and MuseNet for music composition [4][5][6][7]. GANbased technologies such as PGGAN (Progressive Growing of Generative Adversarial Networks), SAGAN (Self-Attention Generative Adversarial Networks), BigGAN, and StyleGAN have been developed; thus improving the position of image generation [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Review on Generative Adversarial Networks: Focusing on Computer Vision and Its Applications

Park

Huh

et al. 2021

Electronics

View full text Add to dashboard Cite

The emergence of deep learning model GAN (Generative Adversarial Networks) is an important turning point in generative modeling. GAN is more powerful in feature and expression learning compared to machine learning-based generative model algorithms. Nowadays, it is also used to generate non-image data, such as voice and natural language. Typical technologies include BERT (Bidirectional Encoder Representations from Transformers), GPT-3 (Generative Pretrained Transformer-3), and MuseNet. GAN differs from the machine learning-based generative model and the objective function. Training is conducted by two networks: generator and discriminator. The generator converts random noise into a true-to-life image, whereas the discriminator distinguishes whether the input image is real or synthetic. As the training continues, the generator learns more sophisticated synthesis techniques, and the discriminator grows into a more accurate differentiator. GAN has problems, such as mode collapse, training instability, and lack of evaluation matrix, and many researchers have tried to solve these problems. For example, solutions such as one-sided label smoothing, instance normalization, and minibatch discrimination have been proposed. The field of application has also expanded. This paper provides an overview of GAN and application solutions for computer vision and artificial intelligence healthcare field researchers. The structure and principle of operation of GAN, the core models of GAN proposed to date, and the theory of GAN were analyzed. Application examples of GAN such as image classification and regression, image synthesis and inpainting, image-to-image translation, super-resolution and point registration were then presented. The discussion tackled GAN’s problems and solutions, and the future research direction was finally proposed.

show abstract

“…Underpinned by empirical studies of real-world systems, complex networks have gained increased interest due to their applicability in various social [26,27,28] and scientific fields, such as biology, economy [29] and geography [30]. For instance, in the economic area it is highly important to understand the mechanism in which certain economic agents handle better than others [31].…”

Section: Social Network Analysismentioning

confidence: 99%

Appliance of network theory in economic geography

Barina¹,

Barina²,

Udrescu³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

A continuously evolving geography requires a good understanding in networks. As such, this paper accounts for theories and applications of complex networks and their role both in geography in general, as well as in determining various geographical network trajectories. It assesses how links between agents lead to an evolutionary process of network retention, as well as network variation, and how geography influences these mechanisms.

show abstract

MuSeNet: Collaboration in the Music Artists Industry

Cited by 18 publications

References 30 publications

Everybody Compose: Deep Beats To Music

Everybody Compose: Deep Beats To Music

Review on Generative Adversarial Networks: Focusing on Computer Vision and Its Applications

Appliance of network theory in economic geography

Contact Info

Product

Resources

About