SDITASApr 29, 2021

Star DGT: a Robust Gabor Transform for Speech Denoising

arXiv:2104.14468v32 citations
Originality Incremental advance
AI Analysis

This addresses speech denoising for applications like audio processing, but it is incremental as it builds on existing Gabor transform methods with a specific window vector.

The paper tackles speech denoising by removing Gaussian, pink, and blue additive noises using a redundant Gabor transform based on a spark-deficient Gabor frame, and it shows that this transform outperforms state-of-the-art baselines consistently across all signals.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes