Sub-Spectrogram Segmentation for Environmental Sound Classification via Convolutional Recurrent Neural Network and Score Level Fusion

Abstract

Environmental Sound Classification (ESC) is an important and challenging problem, and feature representation is a critical and even decisive factor in ESC. Feature representation ability directly affects the accuracy of sound classification. Therefore, the ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. In this paper, we propose a subspectrogram segmentation based ESC classification framework. In addition, we adopt the proposed Convolutional Recurrent Neural Network (CRNN) and score level fusion to jointly improve the classification accuracy. Extensive truncation schemes are evaluated to find the optimal number and the corresponding band ranges of sub-spectrograms. Based on the numerical experiments, the proposed framework can achieve 81.9% ESC classification accuracy on the public dataset ESC-50, which provides 9.1% accuracy improvement over traditional baseline schemes.

arXiv commentaccepted in the 2019 IEEE International Workshop on Signal Processing Systems (SiPS2019)

References in corpus (6)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• mixup: Beyond Empirical Risk Minimization
• Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques
• Acoustic Scene Classification
• Learning from Between-class Examples for Deep Sound Recognition
• SubSpectralNet - Using Sub-Spectrogram based Convolutional Neural Networks for Acoustic Scene Classification