Kumar Krishna, in appreciation

Engel, Michael S.; Grimaldi, David A.

doi:10.3897/zookeys.148.2008

Cited by 2 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What's more, the typical application scenario of Generative Adversarial Network (GAN) is style transfer [11]. Most GAN music generation methods such as GANSYNTH [12] and MuseGAN [13] mainly generate music in imitation, and the generator will be trained to create pieces similar to the given samples. However, GANs require large amounts of data to train and are often accompanied by problems such as mode collapse.…”

Section: Related Work 21 Symbolic Music Generation Using Deep Learningmentioning

confidence: 99%

“…While these methods achieve good results, they suffer from short-term dependency bottlenecks that tend to generate the most believable notes rather than valid harmonic sequences. In addition, many methods based on the Generative Adversarial Network (GAN) have also emerged in recent years [6,11,12]. For the same style of music, 20% of the chord progressions will appear 80% of the time, which constitutes the characteristics of the musical style.…”

Section: Motivation For Reinforcement Learningmentioning

confidence: 99%

See 1 more Smart Citation

DJ-Agent: music theory directed a cappella accompaniment generation using deep reinforcement learning

Jiang

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

This paper proposes a song accompaniment generation method that combines audio analysis and symbolic music generation so that human music theory can be used to build a reinforcement learning model, training an agent to create music. The key to this algorithm is to extract music theory concepts from audio and a reward model that works well in reinforcement learning. However, some music theory rules are complex and challenging to describe. It is difficult to achieve competitive results only by hardcoding the reward. Therefore, to build an effective reward model, a neural network is used to evaluate the perceptual part of composition quality, and program discrimination is used to model easy-to-describe music theory, and the two work together. Experiments show that the proposed algorithm can generate accompaniment arrangements close to human composers, is compatible with various musical styles, and outperforms the baseline algorithm in multiple evaluation metrics.

show abstract

Section: Related Work 21 Symbolic Music Generation Using Deep Learningmentioning

confidence: 99%

Section: Motivation For Reinforcement Learningmentioning

confidence: 99%

DJ-Agent: music theory directed a cappella accompaniment generation using deep reinforcement learning

Jiang

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

show abstract

“…By iteratively updating the generator and discriminator, GANs learn to synthesize samples that mimic intricate patterns, textures, and structures similar to the target data. Recently, GANs have demon-strated groundbreaking results in various domains, including image synthesis, text generation, and music composition [35][36][37][38].…”

Section: Chapter 2 Backgroundmentioning

confidence: 99%

Synthetic Ultrasound Video Generation with Generative Adversarial Networks

Kulik

View full text Add to dashboard Cite

I hereby declare that I am the sole author of this thesis. It is a true copy of the thesis. I certify that, to the best of my knowledge, my work does not infringe upon anyone's copyright nor violate any proprietary rights and that any ideas, techniques, quotations, or any other material from the work of other people included in my thesis, published or otherwise, are fully acknowledged in accordance with the standard referencing practices. The reprint permission is obtained through the publishers.

show abstract

Kumar Krishna, in appreciation

Cited by 2 publications

References 17 publications

DJ-Agent: music theory directed a cappella accompaniment generation using deep reinforcement learning

DJ-Agent: music theory directed a cappella accompaniment generation using deep reinforcement learning

Synthetic Ultrasound Video Generation with Generative Adversarial Networks

Contact Info

Product

Resources

About