Spectral Masking with Explicit Time-Context Windowing for Neural Network-Based Monaural Speech Enhancement

TL;DR

This paper introduces a simple yet effective method for neural speech enhancement that uses explicit time-context windowing to improve spectral masking, boosting speech intelligibility and quality with minimal additional parameters.

Contribution

It presents a novel post-processing approach applying time-context windowing at inference to enhance spectral mask estimation without altering neural network training.

Findings

Improves speech intelligibility and quality in denoising tasks.

Requires less than 1% increase in model parameters.

Effective across different convolutional speech enhancement models.

Abstract

We propose and analyze the use of an explicit time-context window for neural network-based spectral masking speech enhancement to leverage signal context dependencies between neighboring frames. In particular, we concentrate on soft masking and loss computed on the time-frequency representation of the reconstructed speech. We show that the application of a time-context windowing function at both input and output of the neural network model improves the soft mask estimation process by combining multiple estimates taken from different contexts. The proposed approach is only applied as post-optimization in inference mode, not requiring additional layers or special training for the neural network model. Our results show that the method consistently increases both intelligibility and signal quality of the denoised speech, as demonstrated for two classes of convolutional-based speech enhancement models. Importantly, the proposed method requires only a negligible ($\leq1\%$) increase in the number of model parameters, making it suitable for hardware-constrained applications.