Learn2Dance: Learning Statistical Music-to-Dance Mappings for Choreography Synthesis

Ferda Ofli, Engin Erzin, Y. Yemez, A. Murat Tekalp

IEEE Transactions on Multimedia · 2011 · 80 citations · 40 references

Concepts

TL;DR

The study introduces a framework that learns many‑to‑many statistical mappings from musical measures to dance figures to generate music‑driven choreographies. The framework employs four statistical models—HMMs for measure‑to‑figure mapping, clustering for figure diversity, n‑gram for figure transitions, and HMMs for figure motion—combined into a discrete HMM and a modified Viterbi algorithm to synthesize figure sequences, whose motion parameters are computed and animated with a 3‑D character. Objective and subjective evaluations show the framework produces compelling music‑driven choreographies.

Abstract

We propose a novel framework for learning many-to-many statistical mappings from musical measures to dance figures towards generating plausible music-driven dance choreographies. We obtain music-to-dance mappings through use of four statistical models: 1) musical measure models, representing a many-to-one relation, each of which associates different melody patterns to a given dance figure via a hidden Markov model (HMM); 2) exchangeable figures model, which captures the diversity in a dance performance through a one-to-many relation, extracted by unsupervised clustering of musical measure segments based on melodic similarity; 3) figure transition model, which captures the intrinsic dependencies of dance figure sequences via an n-gram model; 4) dance figure models, capturing the variations in the way particular dance figures are performed, by modeling the motion trajectory of each dance figure via an HMM. Based on the first three of these statistical mappings, we define a discrete HMM and synthesize alternative dance figure sequences by employing a modified Viterbi algorithm. The motion parameters of the dance figures in the synthesized choreography are then computed using the dance figure models. Finally, the generated motion parameters are animated synchronously with the musical audio using a 3-D character model. Objective and subjective evaluation results demonstrate that the proposed framework is able to produce compelling music-driven choreographies.

References

40