# Dance Dance Convolution

arXiv: https://arxiv.org/abs/1703.06891 · HTML: https://mlsanity.com/paper/1703.06891/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2017.

## Built on by (most cited first, 12 of 12)

- [Transflower: probabilistic autoregressive dance generation with multimodal attention](https://mlsanity.com/paper/2106.13871/) (2021)
- [Games for Artificial Intelligence Research: A Review and Perspectives](https://mlsanity.com/paper/2304.13269/) (2023)
- [TaikoNation: Patterning-focused Chart Generation for Rhythm Action Games](https://mlsanity.com/paper/2107.12506/) (2021)
- [Gen'eLive! Generating Rhythm Actions in Love Live!](https://mlsanity.com/paper/2202.12823/) (2022)
- [Language Models are Drummers: Drum Composition with Natural Language Pre-Training](https://mlsanity.com/paper/2301.01162/) (2023)
- [Sound Check: Auditing Audio Datasets](https://mlsanity.com/paper/2410.13114/) (2024)
- [Online Game Level Generation from Music](https://mlsanity.com/paper/2207.05271/) (2022)
- [Threshold Designer Adaptation: Improved Adaptation for Designers in Co-creative Systems](https://mlsanity.com/paper/2205.09269/) (2022)
- [Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts](https://mlsanity.com/paper/2311.13687/) (2023)
- [Ordinal Regression for Difficulty Estimation of StepMania Levels](https://mlsanity.com/paper/2301.09485/) (2023)
- [Level generation for rhythm VR games](https://mlsanity.com/paper/2304.06809/) (2023)
- [ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generation](https://mlsanity.com/paper/2607.12857/) (2026)

## Abstract (arXiv)

Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players perform steps on a dance platform in synchronization with music as directed by on-screen step charts. While many step charts are available in standardized packs, players may grow tired of existing charts, or wish to dance to a song for which no chart exists. We introduce the task of learning to choreograph. Given a raw audio track, the goal is to produce a new step chart. This task decomposes naturally into two subtasks: deciding when to place steps and deciding which steps to select. For the step placement task, we combine recurrent and convolutional neural networks to ingest spectrograms of low-level audio features to predict steps, conditioned on chart difficulty. For step selection, we present a conditional LSTM generative model that substantially outperforms n-gram and fixed-window approaches.