Analysis of Noise Reduction Techniques in Speech Recognition

被引：0

作者：

Zheng, Bo ^{[1
]}

Hu, Jinsong ^{[1
]}

Zhang, Ge ^{[2
]}

Wu, Yuling ^{[2
]}

Deng, Jianshuang ^{[3
]}

机构：

[1] South China Univ Technol, Guangzhou, Peoples R China

[2] Guangzhou Power Supply Co Ltd, Power Dispatching & Controlling Ctr, Syst Operat Dept, Guangzhou, Peoples R China

[3] Guangzhou Kinth Network Technol Co Ltd, Guangzhou, Peoples R China

来源：

PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020) | 2020年

关键词：

speech recognition; noise reduction; speech enhancement; signal processing; SPECTRAL SUBTRACTION;

D O I：

10.1109/itnec48623.2020.9084906

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Compared with keyboard input, speech recognition has its strengths it is more in line with the natural communication of people and frees people's hands. In recent years, with the development of artificial intelligence, speech recognition technology has developed rapidly, and the recognition rate is generally in excess of 90%. However, in the case of environmental noise, recognition rates of current speech recognition products have been severely reduced, and most of them cannot work normally. How to enhance these voices with noise and restore the information of the original signal to the greatest extent is an urgent problem. This article summarizes some current mainstream noise reduction algorithms, and compares them by explaining principles of these algorithms. Finally, this article makes a brief prediction of the general development direction of the speech enhancement field in the future.

引用

页码：928 / 933

页数：6

共 16 条

[1] Benesty Jacob, 2007, Springer handbook of speech processing, DOI DOI 10.1007/978-3-540-49127-9
[2] Learning Deep Architectures for AI
Bengio, Yoshua
[J]. FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01): : 1 - 127
[3] Berouti M., 1979, ICASSP 79. 1979 IEEE International Conference on Acoustics, Speech and Signal Processing, P208
[4] SUPPRESSION OF ACOUSTIC NOISE IN SPEECH USING SPECTRAL SUBTRACTION
BOLL, SF
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1979, 27 (02): : 113 - 120
[5] SPEECH ENHANCEMENT USING A MINIMUM MEAN-SQUARE ERROR SHORT-TIME SPECTRAL AMPLITUDE ESTIMATOR
EPHRAIM, Y
MALAH, D
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1984, 32 (06): : 1109 - 1121
[6] Spectral subtraction using reduced delay convolution and adaptive averaging
Gustafsson, H
Nordholm, SE
Claesson, I
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001, 9 (08): : 799 - 807
[7] Adaptive two-band spectral subtraction with multi-window spectral estimation
He, C
Zweig, G
[J]. ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 793 - 796
[8] Reducing the dimensionality of data with neural networks
Hinton, G. E.
Salakhutdinov, R. R.
[J]. SCIENCE, 2006, 313 (5786) : 504 - 507
[9] Factors influencing intelligibility of ideal binary-masked speech: Implications for noise reduction
Li, Ning
Loizou, Philipos C.
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2008, 123 (03) : 1673 - 1682
[10] Liu J., 2017, 2017 12 IEEE C IND E

← 1 2 →