Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning

Abstract

Dancing to music is one of human's innate abilities since ancient times. In machine learning research, however, synthesizing dance movements from music is a challenging problem. Recently, researchers synthesize human motion sequences through autoregressive models like recurrent neural network (RNN). Such an approach often generates short sequences due to an accumulation of prediction errors that are fed back into the neural network. This problem becomes even more severe in the long motion sequence generation. Besides, the consistency between dance and music in terms of style, rhythm and beat is yet to be taken into account during modeling. In this paper, we formalize the music-conditioned dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance. Furthermore, we propose a novel curriculum learning strategy to alleviate error accumulation of autoregressive models in long motion sequence generation, which gently changes the training process from a fully guided teacher-forcing scheme using the previous ground-truth movements, towards a less guided autoregressive scheme mostly using the generated movements instead. Extensive experiments show that our approach significantly outperforms the existing state-of-the-arts on automatic metrics and human evaluation. We also make a demo video to demonstrate the superior performance of our proposed approach at https://www.youtube.com/watch?v=lmE20MEheZ8.

This paper includes the unrigorous quantitative experimental results and has been withdrawn from the conference

References in corpus (10)

• Sequence to Sequence Learning with Neural Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• WaveNet: A Generative Model for Raw Audio
• Generating Long Sequences with Sparse Transformers
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• Video-to-Video Synthesis
• Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio
• Listen to Dance: Music-driven choreography generation using Autoregressive Encoder-Decoder Network
• Bridging the Gap between Training and Inference for Neural Machine Translation
• Music-oriented Dance Video Synthesis with Pose Perceptual Loss

Cited by in corpus (6)

• DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation
• Dual Learning Music Composition and Dance Choreography
• Dance2Music: Automatic Dance-driven Music Generation
• Exploring Multi-Modal Control in Music-Driven Dance Generation
• A Two-part Transformer Network for Controllable Motion Synthesis
• DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning