Star DGT: a Robust Gabor Transform for Speech Denoising

TL;DR

This paper introduces a new robust Gabor transform for speech denoising that outperforms existing methods by leveraging a novel eigenvector-based window in a highly redundant analysis-sparse representation.

Contribution

The paper proposes a novel spark deficient Gabor frame using an eigenvector of the Zauner matrix, improving speech denoising performance over existing Gabor transforms.

Findings

Proposed Gabor transform outperforms state-of-the-art methods

Consistent improvements across different noise types

Effective in real-world speech denoising scenarios

Abstract

In this paper, we address the speech denoising problem, where Gaussian, pink and blue additive noises are to be removed from a given speech signal. Our approach is based on a redundant, analysis-sparse representation of the original speech signal. We pick an eigenvector of the Zauner unitary matrix and -- under certain assumptions on the ambient dimension -- we use it as window vector to generate a spark deficient Gabor frame. The analysis operator associated with such a frame, is a (highly) redundant Gabor transform, which we use as a sparsifying transform in denoising procedure. We conduct computational experiments on real-world speech data, using as baseline three Gabor transforms generated by state-of-the-art window vectors in time-frequency analysis and compare their performance to the proposed Gabor transform. The results show that our proposed redundant Gabor transform outperforms all others, consistently for all signals.