Objective Models for Perceptual Vacuum Cleaner Noise

In this paper, we examine objective models to measure perceptual vacuum cleaner noise. We chose fourteen consumer vacuum cleaners and recorded their noise levels in an anechoic-chamber and a real-life apartment. Then, twelve features were computed to measure the perceptual noise levels. In order to obtain the perceptual noise scores, subjective scores were obtained from 100 evaluators using the paired comparison (PC) method. We tested objective models using the twelve features, which showed high correlations with those subjective scores.