eduzhai > Applied Sciences > Engineering >

A Deep Neural Network for Audio Classification with a Classifier Attention Mechanism

  • Save

... pages left unread,continue reading

Document pages: 15 pages

Abstract: Audio classification is considered as a challenging problem in patternrecognition. Recently, many algorithms have been proposed using deep neuralnetworks. In this paper, we introduce a new attention-based neural networkarchitecture called Classifier-Attention-Based Convolutional Neural Network(CAB-CNN). The algorithm uses a newly designed architecture consisting of alist of simple classifiers and an attention mechanism as a classifier selector.This design significantly reduces the number of parameters required by theclassifiers and thus their complexities. In this way, it becomes easier totrain the classifiers and achieve a high and steady performance. Our claims arecorroborated by the experimental results. Compared to the state-of-the-artalgorithms, our algorithm achieves more than 10 improvements on all selectedtest scores.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×