Sound localization: Human vs. machine

Abstract

The Human shows a remarkable capability in localizing a sound source and navigating towards it. In the current context of robotic applications, machinery models have been developed, so that they can be used in sound source localization. But, it is not yet quantified the accuracy of human's sound source localization in different frequencies and distances at the free field. Thus, the aim of this paper is to estimate the error of human's sound source localization at different frequencies and distances on the horizontal plane and the paper presents the characteristics of ear by taking each individual's localization ability into consideration. An experiment is conducted to investigate the individual ability to predict the sound incident direction. Ten samples of Asian young adults from the age group of 20–30 years are taken into the experiment and their responses for localization cues are recorded. The experiment is also conducted for different sound source locations such as lm, 2m and 3m and different sound source frequencies of 1 kHz and 5 kHz. The results show the individual responses for the direction prediction and they are unique from each individual to the other. The average percentage errors for direction prediction at 1 kHz frequency sound signal give 0.20, 0.93 and 5.20 for lm, 2m and 3m distances respectively. Also, the average percentage errors for direction prediction at 5 kHz frequency sound signal give 3.59, 1.68 and 0.52 for lm, 2m and 3m distances respectively.