DEEP NEURAL NETWORK DERIVED BOTTLENECK FEATURES FOR ACCURATE AUDIO CLASSIFICATION

In this paper, we propose to use deep neural network (DNN) as an effective tool for audio feature extraction. The DNN-derived features can be effectively used in a subsequent classifier (e.g., an SVM in this study) for audio classification. Specifically, we learn bottleneck features from a multi-layer perceptron (MLP), in which Mel filter bank feature is used as network input and one of the hidden layers has a small number of hidden units, compared to the size of the other hidden layers. The narrow hidden layer is served as a bottleneck layer, which creates a constriction in the network that forces the information pertinent to classification into a compact feature representation. We study both unsupervised and supervised bottleneck feature extraction methods and demonstrate that the supervised bottleneck features outperform conventional hand-crafted features and achieve the state-of-the-art performance in audio classification.