论文信息 - ACOUSTIC SCENE CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS AND DIFFERENT CHANNELS REPRESENTATIONS AND ITS FUSION Technical Report

ACOUSTIC SCENE CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS AND DIFFERENT CHANNELS REPRESENTATIONS AND ITS FUSION Technical Report

Deep convolutional neural networks has great results in a image classification tasks. In this paper, we used different architectures of DCNN for image classification. As for images we used spectrograms of differenet signal representations, such as MFCC, Melspectrograms and CQT-spectrograms. Result was obtained using goemetric mean of all the models.

Golubkov Alexander

[1] Kyogu Lee,et al. Convolutional Neural Networks with Binaural Representations and Background Subtraction for Acoustic Scene Classification , 2017, DCASE.

[2] Shao-Hu Peng,et al. Acoustic Scene Classification Using Deep Convolutional Neural Network and Multiple Spectrograms Fusion , 2017, DCASE.