AclNet: efficient end-to-end audio classification CNN

Abstract

We propose an efficient end-to-end convolutional neural network architecture, AclNet, for audio classification. When trained with our data augmentation and regularization, we achieved state-of-the-art performance on the ESC-50 corpus with 85:65% accuracy. Our network allows configurations such that memory and compute requirements are drastically reduced, and a tradeoff analysis of accuracy and complexity is presented. The analysis shows high accuracy at significantly reduced computational complexity compared to existing solutions. For example, a configuration with only 155k parameters and 49:3 million multiply-adds per second is 81:75%, exceeding human accuracy of 81:3%. This improved efficiency can enable always-on inference in energy-efficient platforms.

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• mixup: Beyond Empirical Risk Minimization
• A Closer Look at Weak Label Learning for Audio Events

Cited by in corpus (7)

• Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices
• Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices
• Context, Attention and Audio Feature Explorations for Audio Visual Scene-Aware Dialog
• InfantNet: A Deep Neural Network for Analyzing Infant Vocalizations
• GISE-51: A scalable isolated sound events dataset
• Leveraging Topics and Audio Features with Multimodal Attention for Audio Visual Scene-Aware Dialog
• Exploring Context, Attention and Audio Features for Audio Visual Scene-Aware Dialog