Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks

Understand

We present in this paper a simple, yet efficient convolutional neural network (CNN) architecture for robust audio event recognition.

• Opposing to deep CNN architectures with multiple convolutional and pooling layers topped up with multiple fully connected layers, the proposed network consists of only three layers: convolutional, pooling, and softmax layer.
• Two further features distinguish it from the deep architectures that have been proposed for the task: varying-size convolutional filters at the convolutional layer and 1-max pooling scheme at the pooling layer.
• In intuition, the network tends to select the most discriminative features from the whole audio signals for recognition.