We describe in this chapter a consistent set of temporal models that we have developed over the years for analyzing movement in real-time musical interaction. These models are probabilistic and can be unified and generalized under the formalism of dynamic Bayesian networks (DBNs). We believe that this unified approach offers new perspectives for embodied music cognition and interaction, both in terms of fundamental studies and technological development, as this will be discussed after the general presentation of the framework and the review of specific models previously implemented.