2017
DOI: 10.1587/transinf.2016edp7350
|View full text |Cite
|
Sign up to set email alerts
|

A Speech Enhancement Method Based on Multi-Task Bayesian Compressive Sensing

Abstract: SUMMARYTraditional speech enhancement (SE) algorithms usually have fluctuant performance when they deal with different types of noisy speech signals. In this paper, we propose multi-task Bayesian compressive sensing based speech enhancement (MT-BCS-SE) algorithm to achieve not only comparable performance to but also more stable performance than traditional SE algorithms. MT-BCS-SE algorithm utilizes the dependence information among compressive sensing (CS) measurements and the sparsity of speech signals to per… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
4
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(6 citation statements)
references
References 21 publications
0
4
0
Order By: Relevance
“…The theory of CS was initially proposed for the low-rate image acquisition method. It is then developed for many other applications such as human activity recognition [75], face recognition [76,77], gait recognition [78], wireless sensors networks [79,80], cognitive radio networks [81,22], sound localization [83], audio processing [84,85], radar imaging [86,87], image processing [88,89], and video processing [90,91]. Similarly, CS has contributed to various neural engineering research including, neuronal network connectivity [92], MRI acquisitions [93], MRI reconstruction [94], EEG monitoring [95], compressive imaging [96,97], and other applications.…”
Section: Literature Review: Compressive Sensingmentioning
confidence: 99%
“…The theory of CS was initially proposed for the low-rate image acquisition method. It is then developed for many other applications such as human activity recognition [75], face recognition [76,77], gait recognition [78], wireless sensors networks [79,80], cognitive radio networks [81,22], sound localization [83], audio processing [84,85], radar imaging [86,87], image processing [88,89], and video processing [90,91]. Similarly, CS has contributed to various neural engineering research including, neuronal network connectivity [92], MRI acquisitions [93], MRI reconstruction [94], EEG monitoring [95], compressive imaging [96,97], and other applications.…”
Section: Literature Review: Compressive Sensingmentioning
confidence: 99%
“…This work also shows the success of using compressed feature learning, which reduces the computational energy for analysis due to a reduction in reconstruction costs. In order to leverage the benefits of compressed-domain feature extraction, R. Aghazadeh et al [14] also proposed a new algorithm for epileptic seizure detection using a compressively sensed multichannel EEG signal. S. Qiu et al [61] utilized the concept of feature extraction from the compressed measurements and proposed a teleoperation control system for robotic exoskeleton performing manipulation tasks.…”
Section: Feature Extraction Applicationmentioning
confidence: 99%
“…The theory of CS was initially proposed for low-rate image acquisition. It was then developed for many other applications such as ultrasound imaging [ 5 ], face recognition [ 6 , 7 ], single- pixel camera [ 8 ], wireless sensors networks [ 9 , 10 ], cognitive radio networks [ 11 , 12 ], sound localization [ 13 ], audio processing [ 14 , 15 ], radar imaging [ 16 , 17 ], image processing [ 18 , 19 ], and video processing [ 20 , 21 ]. Similarly, CS has contributed to various neural engineering research including, neuronal network connectivity [ 22 ], magnetic resonance image (MRI) acquisition [ 23 ], MRI reconstruction [ 24 ], electroencephalogram (EEG) monitoring [ 25 ], compressive imaging [ 26 , 27 ], and other applications.…”
Section: Introductionmentioning
confidence: 99%
“…Speech Processing [11]. This indicates that a small number of linear projections can better reconstruct the original signal than a large number of linear projections.…”
Section: Introductionmentioning
confidence: 99%