Designing a Symbol Classifier for Inaudible Sound Communication Systems Using a Neural Network
Kosei Ozeki, Naofumi Aoki, Saki Anazawa, Yoshinori Dobashi, Kenichi Ikeda, Hiroshi Yasuda · 2020
This study has developed a system that performs data communications using high frequency inaudible band of sound signals. Unlike radio communication systems using specified wireless devices, it only requires microphones and speakers employed in ordinary telephony communication systems. In this study, we investigate the possibility of a machine learning approach to improve the recognition accuracy identifying binary symbols transmitted through sound signals. This paper describes some experiments evaluating the performance of our proposed technique employing a neural network as its classifier. The experimental results indicate that the proposed technique may have certain appropriateness for designing an optimal classifier for the symbol identification.