Machine Learning Analysis of Binaural Rowing Sounds

Leonard Johard^*, Emanuele Ruffaldi^*, Pablo Hoffmann^† and Alessandro Filippeschi^*

^(*) PERCRO Lab, Scuola Superiore S.Anna, Pisa, Italy
^(†) Department of Electronic Systems, Aalborg University, Denmark
E-mail: l.johard@sssup.it, e.ruffaldi@sssup.it, pfh@es.aau.dk

Abstract

Techniques for machine hearing are increasing their potentiality due to new application domains. In this work we are addressing the analysis of rowing sounds in natural context for the purpose of supporting a training system based on virtual environments. This paper presents the acquisition methodology and the evaluation of different machine learning techniques for classifying rowing-sound data. We see that a combination of principal component analysis and shallow networks perform equally well as deep architectures, while being much faster to train.