Graph-based Polyphonic Multitrack Music Generation
Not on the map. Why?
Abstract (arXiv)
Graphs can be leveraged to model polyphonic multitrack symbolic music, where notes, chords and entire sections may be linked at different levels of the musical hierarchy by tonal and rhythmic relationships. Nonetheless, there is a lack of works that consider graph representations in the context of deep learning systems for music generation. This paper bridges this gap by introducing a novel graph representation for music and a deep Variational Autoencoder that generates the structure and the content of musical graphs separately, one after the other, with a hierarchical architecture that matches the structural priors of music. By separating the structure and content of musical graphs, it is possible to condition generation by specifying which instruments are played at certain times. This opens the door to a new form of human-computer interaction in the context of music co-creation. After training the model on existing MIDI datasets, the experiments show that the model is able to generate appealing short and long musical sequences and to realistically interpolate between them, producing music that is tonally and rhythmically consistent. Finally, the visualization of the embeddings shows that the model is able to organize its latent space in accordance with known musical concepts.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 27 Jul 2023.
Builds on
29 of 51 references.
References · 29
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2015Gated Graph Sequence Neural Networkscited by 792
- 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
- 2023MusicLM: Generating Music From Textcited by 442
- 2015Adversarial Autoencoderscited by 359
17 more
- 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
- 2017MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompanimentcited by 151
- 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
- 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
- 2019A Gentle Introduction to Deep Learning for Graphscited by 107
- 2017MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generationcited by 72
- 2019Counterpoint by Convolutioncited by 42
- 2018MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfercited by 33
- 2020PIANOTREE VAE: Structured Representation Learning for Polyphonic Musiccited by 25
- 2021MELONS: generating melody with long-term structure using transformers and structure graphcited by 18
- 2016Song From PI: A Musically Plausible Network for Pop Music Generationcited by 13
- 2022Cadence Detection in Symbolic Classical Music using Graph Neural Networkscited by 11
- 2017JamBot: Music Theory Aware Chord Based Generation of Polyphonic Music with LSTMscited by 4
- 2020Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoderscited by 4
- 2017On the Complex Network Structure of Musical Pieces: Analysis of Some Use Cases from Different Music Genrescited by 2
- 2016On the Modeling of Musical Solos as Complex Networkscited by 1
- 2021Calliope -- A Polyphonic Music Transformercited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.