Towards Movement Generation with Audio Features
This work addresses the problem of generating realistic and audio-responsive dance movements for artists and animators, representing an incremental step in motion synthesis.
This paper explores the relationship between sound and movement by developing a movement generation model that incorporates high-level audio features. The model, trained on improvised dance motion capture data, successfully generates realistic dance movements that vary based on the input audio features.
Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.