Generative Choreography using Deep Learning

Abstract

Recent advances in deep learning have enabled the extraction of high-level features from raw sensor data which has opened up new possibilities in many different fields, including computer generated choreography. In this paper we present a system chor-rnn for generating novel choreographic material in the nuanced choreographic language and style of an individual choreographer. It also shows promising results in producing a higher level compositional cohesion, rather than just generating sequences of movement. At the core of chor-rnn is a deep recurrent neural network trained on raw motion capture data and that can generate new dance sequences for a solo dancer. Chor-rnn can be used for collaborative human-machine choreography or as a creative catalyst, serving as inspiration for a choreographer.

arXiv commentThis article will be presented at the 7th International Conference on Computational Creativity, ICCC2016

References in corpus (2)

• Deep Learning in Neural Networks: An Overview
• LSTM: A Search Space Odyssey

Cited by in corpus (6)

• Learning to Generate Diverse Dance Motions with Transformer
• Deep Audio-Visual Learning: A Survey
• Creative Robot Dance with Variational Encoder
• Beyond Imitation: Generative and Variational Choreography via Machine Learning
• Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
• Real-time interactive sequence generation and control with Recurrent Neural Network ensembles