Sample Dropout for Audio Scene Classification Using Multi-Scale Dense Connected Convolutional Neural Network

no code implementations • 12 Jun 2018 • Dawei Feng, Kele Xu, Haibo Mi, Feifan Liao, Yan Zhou

In this paper, we explore the use of multi-scale Dense connected convolutional neural network (DenseNet) for the classification task, with the goal to improve the classification performance as multi-scale features can be extracted from the time-frequency representation of the audio signal.

Acoustic Scene Classification Classification +3