Listen to Dance: Music-driven choreography generation using Autoregressive Encoder-Decoder Network

TLDR

Automatic choreography generation is challenging because it requires aligning music and dance across audio and video modalities. This paper proposes a music‑driven choreography generation system using an autoregressive encoder‑decoder network. The system trains on paired audio‑video clips by extracting dancer joint coordinates and mel‑spectrograms, then generates new dance motion from music alone at inference. A user study shows the model produces musically coherent and natural dance movements for unseen songs.

Abstract

Automatic choreography generation is a challenging task because it often requires an understanding of two abstract concepts - music and dance - which are realized in the two different modalities, namely audio and video, respectively. In this paper, we propose a music-driven choreography generation system using an auto-regressive encoder-decoder network. To this end, we first collect a set of multimedia clips that include both music and corresponding dance motion. We then extract the joint coordinates of the dancer from video and the mel-spectrogram of music from audio, and train our network using music-choreography pairs as input. Finally, a novel dance motion is generated at the inference time when only music is given as an input. We performed a user study for a qualitative evaluation of the proposed method, and the results show that the proposed model is able to generate musically meaningful and natural dance movements given an unheard song.