DCASE 2018 Challenge: Solution for Task 5
This is an incremental improvement for researchers in acoustic scene classification, specifically targeting domestic activity recognition.
The paper tackled the problem of classifying domestic activities in the DCASE 2018 challenge by proposing an ensemble learning system, achieving an F1-score of 92.19% and improving over the baseline by 7.69%.
To address Task 5 in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 challenge, in this paper, we propose an ensemble learning system. The proposed system consists of three different models, based on convolutional neural network and long short memory recurrent neural network. With extracted features such as spectrogram and mel-frequency cepstrum coefficients from different channels, the proposed system can classify different domestic activities effectively. Experimental results obtained from the provided development dataset show that good performance with F1-score of 92.19% can be achieved. Compared with the baseline system, our proposed system significantly improves the performance of F1-score by 7.69%.