Search for Articles:

Recently Downloaded: Paper ID: ART20194107, Total 2616 Articles Downloaded Today



Noise Removal in Speech Signal using Modified Berouti Spectral Subtraction for Emotion Recognition

May Mon Lynn, Chaw Su

Abstract: In this paper, Berouti Spectral subtraction is used for reducing noise from noisy speech signals. It calculates the spectrum of the noisy speech using the combination of Fast Fourier Transform (FFT) and spectral flux and then the noise spectrum is subtracted from the noisy speech spectrum. The performance of this paper was measured by calculating the Signal to Noise Ratio (SNR). This paper proposes a new parameter for speech enhancement. The idea is to apply the spectral subtraction with spectral flux for estimating the noise more precisely. The new parameter is used for spectral subtraction in unvoiced speech frames and the existing power factor in spectral subtraction method is improved.

Keywords: Speech Enhancement, Spectral Subtraction, Spectral Flux, Emotion Recognition

Country: Burma, Subject Area: Digital Signal Processing

Pages: 1640 - 1644

Edition: Volume 8 Issue 5, May 2019

How to Cite this Article?

May Mon Lynn, Chaw Su, "Noise Removal in Speech Signal using Modified Berouti Spectral Subtraction for Emotion Recognition", International Journal of Science and Research (IJSR), https://www.ijsr.net/archive/v8i5/show_abstract.php?id=ART20197721, Volume 8 Issue 5, May 2019, 1640 - 1644

Download PDF


Viewed 45 times.

Downloaded 18 times.