Data-Driven Stastical Modeling of Violin Bowing Gesture Parameter Contours

We present a framework for modeling right-hand gestures in bowed-string instrument playing, applied to violin. Nearly non-intrusive sensing techniques allow for accurate acquisition of relevant timbre-related bowing gesture parameter cues. We model the temporal contour of bow transversal velocity, bow pressing force, and bow-bridge distance as sequences of short segments, in particular Bézier cubic curve segments. Considering different articulations, dynamics, and contexts, a number of note classes is defined. Gesture parameter contours of a performance database are analyzed at note-level by following a predefined grammar that dictates characteristics of curve segment sequences for each of the classes into consideration. Based on dynamic programming, gesture parameter contour analysis provides an optimal curve parameter vector for each note. The information present in such parameter vector is enough for reconstructing original gesture parameter contours with significant fidelity. From the resulting representation vectors, we construct a statistical model based on Gaussian mixtures, suitable for both analysis and synthesis of bowing gesture parameter contours. We show the potential of the model by synthesizing bowing gesture parameter contours from an annotated input score. Finally, we point out promising applications and developments.