Kullback-Leibler Divergence Frequency Warping Scale for Acoustic Scene Classification Using Convolutional Neural Network

Yuhong Yang; Huiyu Zhang; Weiping Tu; Haojun Ai; Linjun Cai; Ruimin Hu; Fei Xiang

ICASSP 2019accepted0 citations

Kullback-Leibler Divergence Frequency Warping Scale for Acoustic Scene Classification Using Convolutional Neural Network

Yuhong Yang, Huiyu Zhang, Weiping Tu, Haojun Ai, Linjun Cai, Ruimin Hu, Fei Xiang

Abstract

Most of current best performing Acoustic Scene Classification (ASC) systems utilize Mel scale spectrograms with Convolutional Neural Networks (CNNs). Mel scale is a common way to suit frequency warping of human ears, with strict decreasing frequency resolution on low to high frequency range. However, we find that significant frequency bins are located at mid to high frequency range for some acoustic scenes, such as travelling by bus, tram or train. In this paper, we show that a better frequency warping scale for ASC can be automatically learned from raw spectrograms, using Kullback-Leibler (KL) divergence scale. Our KL scale spectrograms with CNN method is evaluated on two public ASC datasets. The results show that we outperform the Mel scale method on both datasets. In addition, we also employ a Conditional Generative Adversarial Nets (Conditional-GAN) model for data augmentation, to prevent overfitting problem and allow further improvements on ASC.

BibTeX

@inproceedings{icassp2019_kullbackleiblerd,
  title = {Kullback-Leibler Divergence Frequency Warping Scale for Acoustic Scene Classification Using Convolutional Neural Network},
  author = {Yuhong Yang and Huiyu Zhang and Weiping Tu and Haojun Ai and Linjun Cai and Ruimin Hu and Fei Xiang},
  booktitle = {ICASSP 2019},
  year = {2019}
}