Music- and Lyrics-driven Dance Synthesis
This addresses the need for semantic-rich dance choreography in the entertainment or animation domains, though it is incremental by adding lyrics to existing music-driven methods.
The authors tackled the problem of dance synthesis by introducing the first dataset with dance motion, music, and lyrics, and developed a cross-modal diffusion network to generate 3D dance motion from music and lyrics, achieving a dataset of 4.6 hours across 1867 sequences.
Lyrics often convey information about the songs that are beyond the auditory dimension, enriching the semantic meaning of movements and musical themes. Such insights are important in the dance choreography domain. However, most existing dance synthesis methods mainly focus on music-to-dance generation, without considering the semantic information. To complement it, we introduce JustLMD, a new multimodal dataset of 3D dance motion with music and lyrics. To the best of our knowledge, this is the first dataset with triplet information including dance motion, music, and lyrics. Additionally, we showcase a cross-modal diffusion-based network designed to generate 3D dance motion conditioned on music and lyrics. The proposed JustLMD dataset encompasses 4.6 hours of 3D dance motion in 1867 sequences, accompanied by musical tracks and their corresponding English lyrics.