Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification

• Published in: IEEE signal processing letters Vol. 24; no. 3; pp. 279 - 283
• Main Authors: Salamon, Justin, Bello, Juan Pablo
• Format: Journal Article
• Language: English
• Published: IEEE 01.03.2017
• Subjects: Convolution; Data models; Deep convolutional neural networks (CNNs); deep learning; environmental sound classification; Neural networks; Shape; Time-frequency analysis; Training; Training data; urban sound dataset

The ability of deep convolutional neural networks (CNNs) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the exploitation of this family of high-capacity models. This study has...