On The Performance Of Residual Block Design Alternatives In Convolutional Neural Networks For End-to-end Audio Classification

Abstract

Residual learning is a recently proposed learning framework to facilitate the training of very deep neural networks. Residual blocks or units are made of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or residual connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers that make up a residual block. While ResNet architectures for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, few works have adopted ResNet architectures so far for 1D audio classification tasks. Thus, the suitability of different residual block designs for raw audio classification is partly unknown. The purpose of this paper is to analyze and discuss the performance of several residual block implementations with

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynaranjoalcazar2019on

Related papers

• A Deep Neural Network For Audio Classification With A Classifier Attention Mechanism (2020)0.00
• Audio Concept Classification With Hierarchical Deep Neural Networks (2017)0.00
• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Variational Information Bottleneck For Effective Low-resource Audio Classification (2021)7.81
• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28
• Utilizing Domain Knowledge In End-to-end Audio Processing (2017)0.00
• Impact Of Temporal Resolution On Convolutional Recurrent Networks For Audio Tagging And Sound Event Detection (2022)0.00