Abstract
Gestures in music are of paramount importance partly because they are directly linked to musicians' sound and expressiveness. At the same time, current motion capture technologies are capable of detecting body motion/gestures details very accurately. We present a machine learning approach to automatic violin bow gesture classification based on Hierarchical Hidden Markov Models (HHMM) and motion data. We recorded motion and audio data corresponding to seven representative bow techniques (Détaché, Martelé, Spiccato, Ricochet, Sautillé, Staccato, and Bariolage) performed by a professional violin player. We used the commercial Myo device for recording inertial motion information from the right forearm and synchronized it with audio recordings. Data was uploaded into an online public repository. After extracting features from both the motion and audio data, we trained an HHMM to identify the different bowing techniques automatically. Our model can determine the studied bowing techniques with over 94% accuracy. The results make feasible the application of this work in a practical learning scenario, where violin students can benefit from the real-time feedback provided by the system.
Highlights
A gesture is usually defined as a form of non-verbal communication action associated with an intention or an articulation of an emotional state
With the focus on violin performance, as a test case, one of the primary goals of the project is to provide real-time feedback to students about their performance in comparison to good-practice models which are based on recordings of experts
Authors have applied machine learning (k-NN) and real-time onset detection techniques to classify the hit-locations, dynamics and gestural timbres of professional performers with accuracies over 90% on timber estimations and 100% on onset and hit location detection
Summary
A gesture is usually defined as a form of non-verbal communication action associated with an intention or an articulation of an emotional state. It constitutes an intrinsic part of the human language as a natural body-language execution. In highly competitive sports, as well as in music education, gestures are assumed to be automatic-motor abilities, learned by repetition, to execute an action optimally. Those gestures are intended to be part of the performer’s repertoire. Gestures in music are of paramount importance because fine postural and gestural body movements are directly linked to musicians’ expressive capabilities, and they can be understood as well as correct “energy-consumption” habit development to avoid injuries
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have