Research on speech signal de-noising algorithm based on variable step size LMS adaptive filter with strong background noises

Guang-yan Wang; Zhen-hao Yang; Lei Chen; Hai-feng Li

doi:10.1117/12.2631958

14 April 2022 Research on speech signal de-noising algorithm based on variable step size LMS adaptive filter with strong background noises

Guang-yan Wang, Zhen-hao Yang, Lei Chen, Hai-feng Li

Author Affiliations +

Proceedings Volume 12178, International Conference on Signal Processing and Communication Technology (SPCT 2021); 121780K (2022) https://doi.org/10.1117/12.2631958
Event: International Conference on Signal Processing and Communication Technology (SPCT 2021), 2021, Tianjin, China

Abstract

Aiming at the relatively difficult problems of speech signal enhancement and de-noising under low signal-to-noise ratio and strong background noise, this paper adopts three variable step size LMS adaptive filtering algorithms: variable step size LMS algorithm based on sigmoid function product, variable step size LMS algorithm based on adjusting the optimal exponential factor of sigmoid function and variable step size LMS algorithm based on sigmoid function feedback de-noise The speech signals in different noise environments such as factory noise and ocean noise are de-noised. After the pure speech signal is superimposed with - 10dB, - 5dB, 0dB and 5dB Gaussian white noise, pink noise, factory noise and marine noise respectively, the variable step size LMS adaptive noise cancellation processing is carried out. SNR, PESQ and other objective evaluation algorithms are used to evaluate the sound quality of the enhanced speech signal. The simulation and calculation results show that the three variable step size LMS algorithms used in this paper have good de-noising effect on speech signals with strong background noises of low signal-to-noise ratio, and the variable step size LMS algorithm based on sigmoid function feedback control has better de-noising effect than the other two algorithms under this condition.

Citation Download Citation

Guang-yan Wang, Zhen-hao Yang, Lei Chen, and Hai-feng Li "Research on speech signal de-noising algorithm based on variable step size LMS adaptive filter with strong background noises", Proc. SPIE 12178, International Conference on Signal Processing and Communication Technology (SPCT 2021), 121780K (14 April 2022); https://doi.org/10.1117/12.2631958

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Signal to noise ratio

Interference (communication)

Digital filtering

Electronic filtering

Gaussian filters

Databases

Denoising

Show All Keywords

Keywords/Phrases

Search In:

Publication Years