Semi-supervised Speech Enhancement in Envelop and Details Subspaces

TL;DR

This paper introduces a novel speech enhancement framework that decouples noisy speech spectrograms into envelope and detail subspaces, employing low-rank and sparse decomposition techniques to improve speech intelligibility and quality.

Contribution

It presents a new modulation decoupling subspace approach with supervised decomposition schemes and Bayesian learning for robust speech enhancement, outperforming existing algorithms.

Findings

Improved speech intelligibility and perceptual quality.

Outperforms four existing speech enhancement algorithms.

Effective noise reduction in both envelope and detail subspaces.

Abstract

In this study, we propose a modulation decoupling based single channel speech enhancement subspace framework, in which the spectrogram of noisy speech is decoupled as the product of a spectral envelop subspace and a spectral details subspace. This decoupling approach provides a method to specifically work on elimination of those noises that greatly affect the intelligibility. Two supervised low-rank and sparse decomposition schemes are developed in the spectral envelop subspace to obtain a robust recovery of speech components. A Bayesian formulation of non-negative factorization is used to learn the speech dictionary from the spectral envelop subspace of clean speech samples. In the spectral details subspace, a standard robust principal component analysis is implemented to extract the speech components. The validation results show that compared with four speech enhancement algorithms, including MMSE-SPP, NMF-RPCA, RPCA, and LARC, the proposed MS based algorithms achieve satisfactory performance on improving perceptual quality, and especially speech intelligibility.