On a time-frequency blurring operator with applications in data augmentation

2024/05/21 by Halvdansson, Simon
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Functional Analysis (math.FA) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2405.12899

Abstract

Inspired by the success of recent data augmentation methods for signals which act on time-frequency representations, we introduce an operator which convolves the short-time Fourier transform of a signal with a specified kernel. Analytical properties including boundedness, compactness and positivity are investigated from the perspective of time-frequency analysis. A convolutional neural network and a vision transformer are trained to classify audio signals using spectrograms with different augmentation setups, including the above mentioned time-frequency blurring operator, with results indicating that the operator can significantly improve test performance, especially in the data-starved regime.

Related

• SpecMix : A Mixed Sample Data Augmentation method for Training withTime-Frequency Domain Features
• Spectral analysis of signals by time-domain statistical characterization and neural network processing: Application to correction of spectral amplitude alterations in pulse-like waveforms
• Learning Temporal Resolution in Spectrogram for Audio Classification
• Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
• Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks