Open AccessDiscrete S-Transform Based Speech Enhancement
Author(s) -
Guohua Hu,
Rui Li,
Liang Tao
Publication year - 2015
Publication title -
international journal on smart sensing and intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.171
H-Index - 27
ISSN - 1178-5608
DOI - 10.21307/ijssis-2017-851
Subject(s) - speech enhancement , computer science , speech recognition , spectral density , discrete fourier transform (general) , fourier transform , wavelet transform , time domain , frequency domain , inverse , discrete wavelet transform , signal (programming language) , algorithm , wavelet , artificial intelligence , short time fourier transform , mathematics , noise reduction , telecommunications , computer vision , fourier analysis , programming language , geometry , mathematical analysis
S-transform (ST) is an effective time-frequency representation method with the advantages of short-time Fourier transform and wavelet transform. This paper utilizes the advantages of the power spectral subtraction method and the speech enhancement method to presents a novel speech enhancement algorithm based on discrete ST. Firstly, the speech in time domain is transformed by ST to joint time-frequency domain for spectral subtraction so that the clear speech spectrum can be obtained and then the inverse ST is performed to acquire the enhanced speech in time domain. Simulation experiment is done to verify the validity of the method. The experiment results show that the proposed method can effectively enhance the de-noising ability and improve the signal-to-noise ratio
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom