Music Composition with Deep Learning: A Review

Hernandez-Olivan, Carlos; Beltran, Jose R.

doi:10.48550/arxiv.2108.12290

Cited by 9 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models can learn musical features without hand-crafted rules and produce diverse music pieces. However, without studying music repetition and analyzing the music structure, the model tends to lose a specific sense of direction [11] and the generated music tends to be random without rhythmic patterns [34]. Overall, machine learning-based models continue to struggle to adhere to certain key musical ideas in composition and to generate repetitive rhythmic patterns.…”

Section: Related Workmentioning

confidence: 99%

The Beauty of Repetition in Machine Composition Scenarios

Liu

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Repetition, a basic form of artistic creation, appears in most musical works and delivers enthralling aesthetic experiences. However, repetition remains underexplored in terms of automatic music composition. As an initial effort in repetition modelling, this paper focuses on generating motif-level repetitions via domain knowledge-based and example-based learning techniques. A novel repetition transformer (R-Transformer) that combines a Transformer encoder and a repetition-aware learner is trained on a new repetition dataset with 584,329 samples from different categories of motif repetition. The Transformer encoder learns the representation among music notes from the repetition dataset; the novel repetition-aware learner exploits repetitions' unique characteristics based on music theory. Experiments show that, with any given motif, R-Transformer can generate a large number of variable and beautiful repetitions. With ingenious fusion of these high-quality pieces, the musicality and appeal of machine-composed music have been greatly improved. CCS CONCEPTS• Applied computing → Sound and music computing.

show abstract

Section: Related Workmentioning

confidence: 99%

The Beauty of Repetition in Machine Composition Scenarios

Liu

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Symbolic music generation has gained much attention very recently [32]. This section introduces various recent symbolic music generation studies using GANs.…”

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

“…Moreover, as the music piece is continuously being expanded, the influence of the beginning fragment of the piece might diminish over time, as demonstrated in Figure 1. Unlike human composers, even the state-of-theart Transformer models for music generation do not learn to follow some central musical ideas in their compositions, and they tend to lose the sense of a certain direction [27].…”

Section: Prompt-basedmentioning

confidence: 99%

Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer

Shih¹,

Wu²,

Zalkow³

et al. 2021

Preprint

View full text Add to dashboard Cite

Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly trains the Transformer to treat the conditioning sequence as a thematic material that has to manifest itself multiple times in its generation result. This is achieved with two main technical contributions. First, we propose a deep learning-based approach that uses contrastive representation learning and clustering to automatically retrieve thematic materials from music pieces in the training data. Second, we propose a novel gated parallel attention module to be used in a sequence-to-sequence (seq2seq) encoder/decoder architecture to more effectively account for a given conditioning thematic material in the generation process of the Transformer decoder. We report on objective and subjective evaluations of variants of the proposed Theme Transformer and the conventional promptbased baseline, showing that our best model can generate, to some extent, polyphonic pop piano music with repetition and plausible variations of a given condition.

show abstract

Music Composition with Deep Learning: A Review

Cited by 9 publications

References 20 publications

The Beauty of Repetition in Machine Composition Scenarios

The Beauty of Repetition in Machine Composition Scenarios

Difficulty Controlled Piano Music Generation using GAN Approach

Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer

Contact Info

Product

Resources

About