Type/position classification of inter-floor noise in residential buildings with a single microphone via supervised learning

Inter-floor noise propagates through a building structure from a noise source to neighbors on other floors. Identification of type/position of inter-floor noise in a building is difficult for human hearing. A convolutional neural network-based inter-floor noise type/position classification method was proposed in [Appl. Sci. 9, 3735 (2019)] to identify inter-floor noise. The method was evaluated against inter-floor noise collected in a single campus building as a feasibility test. In this work, the generalizability of the method was addressed through numerous tasks using new datasets collected in two real apartment buildings. These datasets contain inter-floor noise generated in rooms and at positions with three-dimensional spatial diversity, which was not studied in the previous work. Furthermore, type classification knowledge transfer between two individual apartment building domains was studied.