DeepAI AI Chat
Log In Sign Up

SubSpectral Normalization for Neural Audio Data Processing

by   Simyung Chang, et al.

Convolutional Neural Networks are widely used in various machine learning domains. In image processing, the features can be obtained by applying 2D convolution to all spatial dimensions of the input. However, in the audio case, frequency domain input like Mel-Spectrogram has different and unique characteristics in the frequency dimension. Thus, there is a need for a method that allows the 2D convolution layer to handle the frequency dimension differently. In this work, we introduce SubSpectral Normalization (SSN), which splits the input frequency dimension into several groups (sub-bands) and performs a different normalization for each group. SSN also includes an affine transformation that can be applied to each group. Our method removes the inter-frequency deflection while the network learns a frequency-aware characteristic. In the experiments with audio data, we observed that SSN can efficiently improve the network's performance.


page 1

page 2

page 3

page 4


A novel audio representation using space filling curves

Since convolutional neural networks (CNNs) have revolutionized the image...

nnAudio: An on-the-fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolution Neural Networks

Converting time domain waveforms to frequency domain spectrograms is typ...

Pixel Normalization from Numeric Data as Input to Neural Networks

Text to image transformation for input to neural networks requires inter...

Positional Normalization

A widely deployed method for reducing the training time of deep neural n...

On the Ideal Number of Groups for Isometric Gradient Propagation

Recently, various normalization layers have been proposed to stabilize t...

Helicality: An Isomap-based Measure of Octave Equivalence in Audio Data

Octave equivalence serves as domain-knowledge in MIR systems, including ...