Complex Clipping for Improved Generalization in Machine Learning

TL;DR

This paper introduces a novel complex clipping method for spectrograms that enhances the generalization ability of machine learning models, especially in noisy acoustic environments, by extending ReLU activation to complex STFT data.

Contribution

It proposes a simple, regularized complex clipping technique for spectrograms that improves training stability and generalization in deep learning models for audio applications.

Findings

Significant improvement in generalization performance on noisy acoustic data

Enhanced training stability with the proposed complex clipping method

Potential applicability to various time-frequency domain applications

Abstract

For many machine learning applications, a common input representation is a spectrogram. The underlying representation for a spectrogram is a short time Fourier transform (STFT) which gives complex values. The spectrogram uses the magnitude of these complex values, a commonly used detector. Modern machine learning systems are commonly overparameterized, where possible ill-conditioning problems are ameliorated by regularization. The common use of rectified linear unit (ReLU) activation functions between layers of a deep net has been shown to help this regularization, improving system performance. We extend this idea of ReLU activation to detection for the complex STFT, providing a simple-to-compute modified and regularized spectrogram, which potentially results in better behaved training. We then confirmed the benefit of this approach on a noisy acoustic data set used for a real-world application. Generalization performance improved substantially. This approach might benefit other applications which use time-frequency mappings, for acoustic, audio, and other applications.