Drum Kit sound localization tests on binaural hearing model with ANN

Binaural hearing is an important ability of humans. While utilizing a binaural hearing model with Artificial Neural Network it is possible to simulate localization of sound source position by humans. In this paper localization of drum kit sounds as well as localization prediction dependence on head related functions used to synthesize these drum kit sounds are concerned. Three separate tests were performed using two classification algorithms: for horizontal plane only, for both horizontal and vertical planes (Koshkina E., Bouse J., Proc. of Poster 2017). In the first test localization of auralized drum kit sounds through different HRTF sets at fixed positions was performed to observe elevation and azimuth prediction differences. In the other two tests localization at unfixed positions for drum kit sounds with and without room reflections was performed.