Star DGT: a Robust Gabor Transform for Speech Denoising

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.

arXiv commentarXiv admin note: text overlap with arXiv:2103.11233

References in corpus (10)

• Templates for Convex Cone Problems with Applications to Sparse Signal Recovery
• Gabor Convolutional Networks
• The Cosparse Analysis Model and Algorithms
• ${\ell }^1$-Analysis Minimization and Generalized (Co-)Sparsity: When Does Recovery Succeed?
• A note on Gabor frames in finite dimensions
• AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks
• Linear Dependencies in Weyl-Heisenberg Orbits
• Single Channel Audio Source Separation using Convolutional Denoising Autoencoders
• Spark deficient Gabor frames
• Spark Deficient Gabor Frame Provides a Novel Analysis Operator for Compressed Sensing