Speech Enhancement Techniques based on Microphone Arrays and Deep Learning

被引：0

作者：

Wang, Xin ^{[1
]}

Guo, Baofeng ^{[1
]}

Huo, Xiaolei ^{[1
]}

Zhang, Yi ^{[1
]}

Tao, Jie ^{[1
]}

机构：

[1] Army Engn Univ, Shijiazhuang Campus, Shijiazhuang, Peoples R China

来源：

2024 IEEE 8TH INTERNATIONAL CONFERENCE ON VISION, IMAGE AND SIGNAL PROCESSING, ICVISP | 2024年

关键词：

microphone array; deep learning; speech enhancement; speech noise reduction;

D O I：

10.1109/ICVISP64524.2024.10959537

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper combines the practical application requirements, studies the characteristics and basic principles of the single speech signal noise environment, with the signal frame structure as the basis of the object, proposed the use of microphone arrays and deep learning combined method of denoising voice signals in complex environments enhancement, through the simulation of the experimental results and the original signal for comparison, verified through the combination of the microphone arrays and deep learning method of voice signal enhancement feasibility, to provide theoretical support and experimental basis for subsequent voice noise reduction. Through the simulation experimental results and the comparison with the original signal, the feasibility of the combination of microphone array and deep learning method for speech signal enhancement is verified, which provides theoretical support and experimental basis for the subsequent speech noise reduction.

引用

页数：4

共 11 条

[1]

Benesty J, 2012, SPRBRIEF ELECT, P51, DOI 10.1007/978-3-642-23250-3_4

[2]

[曹仰杰 Cao Yangjie], 2018, [中国图象图形学报, Journal of Image and Graphics], V23, P1433

[3] Image-to-Image Translation with Conditional Adversarial Networks [J].

Isola, Phillip ;

Zhu, Jun-Yan ;

Zhou, Tinghui ;

Efros, Alexei A. .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :5967-5976

[4]

Jiang Maosong, 2018, Journal of Computer Applications, V38, P1176, DOI 10.11772/j.issn.1001-9081.2017092316

[5]

LIANG Yao, 2018, Information Technology, V42, P24

[6]

LU Zhenyu, 2018, Modern Electronics Technique, V41, P47

[7] Impact of phase estimation on single-channel speech separation based on time-frequency masking [J].

Mayer, Florian ;

Williamson, Donald S. ;

Mowlaee, Pejman ;

Wang, DeLiang .

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2017, 141 (06) :4668-4679

[8]

Papyan V, 2017, J MACH LEARN RES, V18, P1

[9]

YANG Fan, 2022, Computer & Digital Engineering, V50, P344

[10]

Yu D., 2014, Technical Report

← 1 2 →