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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2018aclnet

Related papers

• A Deep Neural Network For Audio Classification With A Classifier Attention Mechanism (2020)0.00
• Effective Audio Classification Network Based On Paired Inverse Pyramid Structure And Dense MLP Block (2022)9.06
• Classifying Variable-length Audio Files With All-convolutional Networks And Masked Global Pooling (2016)0.00
• Enclap: Combining Neural Audio Codec And Audio-text Joint Embedding For Automated Audio Captioning (2024)14.03
• Reducing Model Complexity For DNN Based Large-scale Audio Classification (2017)9.59
• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28
• Audio-based Music Classification With Densenet And Data Augmentation (2019)10.48
• Utilizing Domain Knowledge In End-to-end Audio Processing (2017)0.00