mlsanityData to 7 Oct 2026

CoCoFormer: A controllable feature-rich polyphonic music generation method

arXiv 2310.09843 ↗First posted 15 Oct 2023cs.SD cs.AI eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

This paper explores the modeling method of polyphonic music sequence. Due to the great potential of Transformer models in music generation, controllable music generation is receiving more attention. In the task of polyphonic music, current controllable generation research focuses on controlling the generation of chords, but lacks precise adjustment for the controllable generation of choral music textures. This paper proposed Condition Choir Transformer (CoCoFormer) which controls the output of the model by controlling the chord and rhythm inputs at a fine-grained level. In this paper, the self-supervised method improves the loss function and performs joint training through conditional control input and unconditional input training. In order to alleviate the lack of diversity on generated samples caused by the teacher forcing training, this paper added an adversarial training method. CoCoFormer enhances model performance with explicit and implicit inputs to chords and rhythms. In this paper, the experiments proves that CoCoFormer has reached the current better level than current models. On the premise of specifying the polyphonic music texture, the same melody can also be generated in a variety of ways.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 15 Oct 2023.

Builds on

18 of 35 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  3. 2017Gate-Variants of Gated Recurrent Unit (GRU) Neural Networkscited by 239
  4. 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 223
  5. 2017MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompanimentcited by 151
  6. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  7. 2016DeepBach: a Steerable Model for Bach Chorales Generationcited by 90
  8. 2017MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generationcited by 72
  9. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  10. 2013How to Construct Deep Recurrent Neural Networkscited by 64
  11. 2019LakhNES: Improving multi-instrumental music generation with cross-domain pre-trainingcited by 54
  12. 2018Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architecturescited by 30
6 more
  1. 2018The NES Music Database: A multi-instrumental dataset with expressive performance attributescited by 11
  2. 2014Polyphonic Music Generation by Modeling Temporal Dependencies Using a RNN-DBNcited by 6
  3. 2019Improving Polyphonic Music Models with Feature-Rich Encodingcited by 6
  4. 2019LSTM Based Music Generation Systemcited by 5
  5. 2021JS Fake Chorales: a Synthetic Dataset of Polyphonic Music with Human Annotationcited by 5
  6. 2020Attentional networks for music generationcited by 3

Built on by

Not cited yet.