# Conditional Drums Generation using Compound Word Representations

arXiv: https://arxiv.org/abs/2202.04464 · HTML: https://mlsanity.com/paper/2202.04464/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 9 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [DeepBach: a Steerable Model for Bach Chorales Generation](https://mlsanity.com/paper/1612.01010/) (2016)
- [This Time with Feeling: Learning Expressive Musical Performance](https://mlsanity.com/paper/1808.03715/) (2018)
- [The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures](https://mlsanity.com/paper/2008.01307/) (2020)
- [EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation](https://mlsanity.com/paper/2108.01374/) (2021)
- [Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling](https://mlsanity.com/paper/2007.15474/) (2020)
- [Learning to Groove with Inverse Sequence Transformations](https://mlsanity.com/paper/1905.06118/) (2019)
- [A Functional Taxonomy of Music Generation Systems](https://mlsanity.com/paper/1812.04186/) (2018)
- [MorpheuS: generating structured music with constrained patterns and tension](https://mlsanity.com/paper/1812.04832/) (2018)
- [Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework](https://mlsanity.com/paper/2104.13056/) (2021)
- [High-Level Control of Drum Track Generation Using Learned Patterns of Rhythmic Interaction](https://mlsanity.com/paper/1908.00948/) (2019)
- [Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure](https://mlsanity.com/paper/2102.09794/) (2021)
- [BERT-like Pre-training for Symbolic Piano Music Classification Tasks](https://mlsanity.com/paper/2107.05223/) (2021)
- [Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network](https://mlsanity.com/paper/1807.11161/) (2018)
- [Talking Drums: Generating drum grooves with neural networks](https://mlsanity.com/paper/1706.09558/) (2017)

## Built on by (most cited first, 7 of 7)

- [Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model](https://mlsanity.com/paper/2311.00968/) (2023)
- [JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE](https://mlsanity.com/paper/2210.06007/) (2022)
- [Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey](https://mlsanity.com/paper/2402.17467/) (2024)
- [Motifs, Phrases, and Beyond: The Modelling of Structure in Symbolic Music Generation](https://mlsanity.com/paper/2403.07995/) (2024)
- [LyricJam Sonic: A Generative System for Real-Time Composition and Musical Improvisation](https://mlsanity.com/paper/2210.15638/) (2022)
- [Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models](https://mlsanity.com/paper/2408.02711/) (2024)
- [Can pre-trained Deep Learning models predict groove ratings?](https://mlsanity.com/paper/2603.27237/) (2026)

## Abstract (arXiv)

The field of automatic music composition has seen great progress in recent years, specifically with the invention of transformer-based architectures. When using any deep learning model which considers music as a sequence of events with multiple complex dependencies, the selection of a proper data representation is crucial. In this paper, we tackle the task of conditional drums generation using a novel data encoding scheme inspired by the Compound Word representation, a tokenization process of sequential data. Therefore, we present a sequence-to-sequence architecture where a Bidirectional Long short-term memory (BiLSTM) Encoder receives information about the conditioning parameters (i.e., accompanying tracks and musical attributes), while a Transformer-based Decoder with relative global attention produces the generated drum sequences. We conducted experiments to thoroughly compare the effectiveness of our method to several baselines. Quantitative evaluation shows that our model is able to generate drums sequences that have similar statistical distributions and characteristics to the training corpus. These features include syncopation, compression ratio, and symmetry among others. We also verified, through a listening test, that generated drum sequences sound pleasant, natural and coherent while they "groove" with the given accompaniment.