Jee-weon Jung(University of Seoul), Hye-jin Shim(University of Seoul), Ju-ho Kim(University of Seoul), Seung-bin Kim(University of Seoul) and Ha-Jin Yu(University of Seoul)
Acoustic scene classification systems using deep neural networks classify given recordings into pre-defined classes. In this study, we propose a novel scheme for acoustic scene classification which adopts an audio tagging system inspired by the human perception mechanism. When humans identify an acoustic scene, the existence of different sound events provides discriminative information which affects the judgement. The proposed framework mimics this mechanism using various approaches. Firstly, we employ three methods to concatenate tag vectors extracted using an audio tagging system with an intermediate hidden layer of an acoustic scene classification system. We also explore the multi-head attention on the feature map of an acoustic scene classification system using tag vectors. Experiments conducted on the detection and classification of acoustic scenes and events 2019 task 1-a dataset demonstrate the effectiveness of the proposed scheme. Concatenation and multi-head attention show a classification accuracy of 75.66 % and 76.58 %, respectively, compared to 73.63 % accuracy of the baseline. The system with the proposed two approaches combined demonstrates an accuracy of 76.75 %.