Low rank sparse decomposition model based speech enhancement using gammatone filterbank and Kullback–Leibler divergence

An important stage in speech enhancement is to estimate noise signal which is a difficult task in non-stationary and low signal-to-noise conditions. This paper presents an iterative speech enhancement approach which requires no prior knowledge of noise and is based on low-rank sparse matrix decomposition using Gammatone filterbank and convex distortion measure. To estimate noise and speech, the noisy speech is decomposed into low-rank noise and sparse-speech parts by enforcing sparsity regularization. The exact distribution of noise signals and noise estimator is not required in this approach. The experimental results demonstrate that our approach outperforms competing methods and yields better overall speech quality and intelligibility. Moreover, composite objective measure reinforced a better performance in terms of residual noise and speech distortion in adverse noisy conditions. The time-varying spectral analysis validates significant reduction of the background noise.

Download Full-text

A New Speech Enhancement Method Based on Nonnegative Low-rank and Sparse Decomposition

Journal of Physics Conference Series ◽

10.1088/1742-6596/1848/1/012090 ◽

2021 ◽

Vol 1848 (1) ◽

pp. 012090

Author(s):

Jiayi Sun ◽

Chengli Sun ◽

Yi Hong

Keyword(s):

Speech Enhancement ◽

Low Rank ◽

Sparse Decomposition ◽

Enhancement Method

Download Full-text

Task-free brainprint recognition based on low-rank and sparse decomposition model

International Journal of Data Mining and Bioinformatics ◽

10.1504/ijdmb.2019.100629 ◽

2019 ◽

Vol 22 (3) ◽

pp. 280 ◽

Cited By ~ 2

Author(s):

Wanzeng Kong ◽

Xianghao Kong ◽

Qiaonan Fan ◽

Qibin Zhao ◽

Andrzej Cichocki

Keyword(s):

Low Rank ◽

Sparse Decomposition ◽

Decomposition Model

Download Full-text

Task-free brainprint recognition based on low-rank and sparse decomposition model

International Journal of Data Mining and Bioinformatics ◽

10.1504/ijdmb.2019.10022334 ◽

2019 ◽

Vol 22 (3) ◽

pp. 280

Author(s):

Wanzeng Kong ◽

Xianghao Kong ◽

Qiaonan Fan ◽

Qibin Zhao ◽

Andrzej Cichocki

Keyword(s):

Low Rank ◽

Sparse Decomposition ◽

Decomposition Model

Download Full-text

Fast Low-Rank Decomposition Model-Based Hyperspectral Image Classification Method

IEEE Geoscience and Remote Sensing Letters ◽

10.1109/lgrs.2016.2633322 ◽

2017 ◽

Vol 14 (2) ◽

pp. 169-173 ◽

Cited By ~ 1

Author(s):

Fen Chen ◽

Peng Zhao ◽

Ting Feng Tang ◽

Yan Zhou

Keyword(s):

Image Classification ◽

Hyperspectral Image ◽

Classification Method ◽

Low Rank ◽

Hyperspectral Image Classification ◽

Decomposition Model ◽

Model Based ◽

Rank Decomposition ◽

Low Rank Decomposition

Download Full-text

Low-Rank and Sparse Decomposition Model for Accelerating Dynamic MRI Reconstruction

Journal of Healthcare Engineering ◽

10.1155/2017/9856058 ◽

2017 ◽

Vol 2017 ◽

pp. 1-9 ◽

Cited By ~ 2

Author(s):

Junbo Chen ◽

Shouyin Liu ◽

Min Huang

Keyword(s):

Inverse Problem ◽

Convex Optimization ◽

Principal Component ◽

Dynamic Mri ◽

Low Rank ◽

Cine Image ◽

Sparse Decomposition ◽

Decomposition Model ◽

Reconstruction Methods ◽

Space Data

The reconstruction of dynamic magnetic resonance imaging (dMRI) from partially sampled k-space data has to deal with a trade-off between the spatial resolution and temporal resolution. In this paper, a low-rank and sparse decomposition model is introduced to resolve this issue, which is formulated as an inverse problem regularized by robust principal component analysis (RPCA). The inverse problem can be solved by convex optimization method. We propose a scalable and fast algorithm based on the inexact augmented Lagrange multipliers (IALM) to carry out the convex optimization. The experimental results demonstrate that our proposed algorithm can achieve superior reconstruction quality and faster reconstruction speed in cardiac cine image compared to existing state-of-art reconstruction methods.

Download Full-text