Multi-scale semantic feature fusion and data augmentation for acoustic scene classification. (June 2020)

• Record Type: Journal Article
• Authors: Yang, Liping; Tao, Lianjie; Chen, Xinxing; Gu, Xiaohua
• Is Part Of: Applied acoustics. Volume 163(2020)
• Publication Date: 2020-06
• Subjects: Multi-scale feature learning -- Convolutional neural networks -- Data augmentation -- Acoustic scene classification (ASC) -- Machine listening; Acoustical engineering -- Periodicals; Periodicals; 620.2
• DOI: 10.1016/j.apacoust.2020.107238
• Languages: English
• ISSNs: 0003-682X

Abstract

Abstract: This paper investigates a multi-scale semantic feature fusion and data augmentation approach for deep convolutional neural network (CNN) based acoustic scene classification. To ensemble the multi-scale semantic information of CNN and improve the performance of acoustic scene classification, a multi-scale feature fusion framework, which consists of a simplified Xception backbone and a semantic feature fusion strategy, is presented. A novel label smoothing mixup data augmentation method, which is a generalization of mixup and label smoothing, is proposed to alleviate the over-confident problem of network training. A spatial-mixup technique is presented to generate meaningful mixup virtual data for acoustic scene classification. Extensive experiments on synthetic data and real acoustic scene classification dataset demonstrate that both multi-scale semantic feature fusion and label smoothing spatial-mixup data augmentation are effective for improving the acoustic scene classification performance of a deep neural network.