Audio event classification using deep neural networks

Abstract

We present in this paper our work on audio event classification for outdoor events. As the main classification method we employ a deep neural network (DNN) and compare this to other classification methods. We propose a novel improvement to the pre-training process of the network which is useful when training with Gaussian data. Our experimental results are based on an audio corpus extracted from the FreeSound.org website repository. We show that the DNN has some advantage over other classification methods and that fusion of two methods can produce the best results.