A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification

Abstract

Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up 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 shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their adoption for 1D end-to-end architectures is still scarce in the audio domain. Thus, the suitability of different residual block designs for raw audio classification is partly unknown. The purpose of this paper is to compare, analyze and discuss the performance of several residual block implementations, the most commonly used in image classification problems, within a state-of-the-art CNN-based architecture for end-to-end audio classification using raw audio waveforms. Deep and careful statistical analyses over six different residual block alternatives are conducted, considering two well-known datasets and common input normalization choices. The results show that, while some significant differences in performance are observed among architectures using different residual block designs, the selection of the most suitable residual block can be highly dependent on the input data.

Malicious URL Detection Based on Improved Multilayer Recurrent Convolutional Neural Network Model

“…Network component ResUnit indicates residual connection after two CBM operations. e residual connection solves the problem of gradient disappearance [20]. Its principle is to take the output of the previous layer as the input of the latter layer, so as to create a shortcut to let information directly enter the deep network, which effectively avoids the problems of gradient disappearance and gradient explosion.…”

WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information

“…There are different published approaches for AAC. Regarding input audio encoding, some approaches use recurrent neural networks (RNNs) [2], [3], [4], others 2D convolutional neural networks (CNNs) [5], [6], and some others the Transformer model [7], [8]. Though, RNNs are known to have difficulties on learning temporal information [9], 2D CNNs model time-frequency but not temporal patterns [10], and the Transformer was not originally designed for sequences of thousands time-steps [7].…”

“…Though, RNNs are known to have difficulties on learning temporal information [9], 2D CNNs model time-frequency but not temporal patterns [10], and the Transformer was not originally designed for sequences of thousands time-steps [7]. For generating the captions, the Transformer decoder [6], [11], [8] or RNNs [1], [3], [5] are mostly employed, and the alignment of input audio and output captions is typically implemented with an attention mechanism [12], [11]. Also, some approaches adopt a multitask approach, where the AAC method is regularized by the prediction of keywords, based on the input audio [6], [11], [13].…”