Air Drums, and Bass: Anticipating Musical Gestures in Accelerometer Signals with a Lightweight CNN

Detecting gestures has often been performed using non-causal techniques such as Hidden Markov Models or pick-peaking and thresholding. They can present perceptible delay that harms their use in real-time scenarios, unless a very high sampling rate is used. In this work, we investigate a lightweight CNN-based neural network to predict and anticipate musical cues (i.e., drum hits or note onsets) from accelerometer signals. We show that our architecture is able to anticipate gestures using preparatory movements, such as raising the drumstick, thus being potentially usable in music- or gaming-related interactive devices.

1. Introduction

Modern technology has provided contemporary musicianship with unforeseen perspectives for music production and performance. Nowadays, virtual music instruments and digital audio effects are ubiquitous in recording studios, networked performances are becoming increasingly common, and avant-garde artists are, more and more, experimenting interactions with musical robots. An important advance in the last few decades is to use motion itself to control musical devices, fostering the use of common gestural repertoires and the creation of embodied performances [1].