Speech Enhancement of a Mobile Car-Noisy Speech Using Spectral Subtraction Algorithms

Afolabi, L.O. and Olaiya, O.O Speech Enhancement of a Mobile Car-Noisy Speech Using Spectral Subtraction Algorithms. IJESC, 9 (11). pp. 24092-24096. ISSN 2321 3361

[img] Other
1journal - Copy.PDF

Download (351kB)

Abstract

Problem with speech are background noise from the environment and internal generated noise. Speech enhancements involve reduction of all these noise to a minimum level so has to increase the signal to noise ratio (SNR) without losing the quality and the content of the signal. Many algorithms are used to enhance speech signals but most are not as effective as Spectral subtraction algorithms. Hence, this paper is on the use of Spectral subtraction algorithms to reduce noise generated by mobile car, very close to the speech source. Different sample of polluted noisy speech signal were sample at -5dB, 5dB, 10dB, and so on, Spectral Subtraction noise reduction technique has a limit -5.0000dB to 18.0670dB SNR value for Car Noisy Speech Signal.

Item Type: Article
Uncontrolled Keywords: peech-enhancement, Spectral-subtraction, DFT, Noise signal, VAD
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering, Science and Mathematics > School of Engineering Sciences
Depositing User: Joy Oluwabukola Olayiwola
Date Deposited: 13 Jul 2021 14:48
Last Modified: 13 Jul 2021 14:48
URI: http://eprints.federalpolyilaro.edu.ng/id/eprint/1761

Actions (login required)

View Item View Item