Temporally Guided Music-to-Body-Movement Generation
This work addresses the challenge of creating realistic body movements for virtual musicians, which is incremental as it builds on prior 2-D methods.
The paper tackles the problem of generating 3-D skeleton movements for virtual violinists from music audio, and the result is a model that outperforms state-of-the-art methods in both objective and subjective evaluations.
This paper presents a neural network model to generate virtual violinist's 3-D skeleton movements from music audio. Improved from the conventional recurrent neural network models for generating 2-D skeleton data in previous works, the proposed model incorporates an encoder-decoder architecture, as well as the self-attention mechanism to model the complicated dynamics in body movement sequences. To facilitate the optimization of self-attention model, beat tracking is applied to determine effective sizes and boundaries of the training examples. The decoder is accompanied with a refining network and a bowing attack inference mechanism to emphasize the right-hand behavior and bowing attack timing. Both objective and subjective evaluations reveal that the proposed model outperforms the state-of-the-art methods. To the best of our knowledge, this work represents the first attempt to generate 3-D violinists' body movements considering key features in musical body movement.