A two-stage full-band speech enhancement model with effective spectral compression mapping

TL;DR

This paper introduces a two-stage full-band speech enhancement model that uses spectral compression mapping to better process high frequency components, improving overall speech quality by focusing on the most speech-rich frequency ranges.

Contribution

The paper proposes a novel spectral compression mapping technique and a two-stage enhancement framework that jointly improve full-band speech enhancement performance.

Findings

Effective spectral compression mapping enhances high frequency processing.

Two-stage model achieves higher speech quality in experiments.

Focus on low and middle frequencies improves enhancement results.

Abstract

The direct expansion of deep neural network (DNN) based wide-band speech enhancement (SE) to full-band processing faces the challenge of low frequency resolution in low frequency range, which would highly likely lead to deteriorated performance of the model. In this paper, we propose a learnable spectral compression mapping (SCM) to effectively compress the high frequency components so that they can be processed in a more efficient manner. By doing so, the model can pay more attention to low and middle frequency range, where most of the speech power is concentrated. Instead of suppressing noise in a single network structure, we first estimate a spectral magnitude mask, converting the speech to a high signal-to-ratio (SNR) state, and then utilize a subsequent model to further optimize the real and imaginary mask of the pre-enhanced signal. We conduct comprehensive experiments to validate the efficacy of the proposed method.