Audio signal classification using Linear Predictive Coding and Random Forests

Abstract

The goal of this work is to present an audio signal classification system based on Linear Predictive Coding and Random Forests. We consider the problem of multiclass classification with imbalanced datasets. The signals under classification belong to the class of sounds from wildlife intruder detection applications: birds, gunshots, chainsaws, human voice and tractors. The proposed system achieves an overall correct classification rate of 99.25%. There is no probability of false alarms in the case of birds or human voices. For the other three classes the probability is low, around 0.3%. The false omission rate is also low: around 0.2% for birds and tractors, a little bit higher for chainsaws (0.4%), lower for gunshots (0.14%) and zero for human voices.