Ensemble Of Deep Neural Networks For Acoustic Scene Classification
This work addresses acoustic scene classification for audio processing applications, but it is incremental as it applies existing methods to a new domain.
The paper tackled acoustic scene classification by adapting state-of-the-art deep neural networks from image classification, achieving a 3.1% improvement on the test set and 10% on the development set over the baseline for DCASE-2017 Task 1.
Deep neural networks (DNNs) have recently achieved great success in a multitude of classification tasks. Ensembles of DNNs have been shown to improve the performance. In this paper, we explore the recent state-of-the-art DNNs used for image classification. We modified these DNNs and applied them to the task of acoustic scene classification. We conducted a number of experiments on the TUT Acoustic Scenes 2017 dataset to empirically compare these methods. Finally, we show that the best model improves the baseline score for DCASE-2017 Task 1 by 3.1% in the test set and by 10% in the development set.