Reduction of Impulsive Noise from Speech and Audio Signals by using Sd Rom Algorithm
G.Manmadha Rao1, D.N Raidu Babu2, P.S.L Krishna Kanth3, B.Vinay4, V.Nikhil5
1G.Manmadha Rao*, Department of Electronics and Communication Engineering, Visakhapatnam, (Andhra Pradesh), India.
2D.N Raidu Babu, Department of Electronics and Communication Engineering, Visakhapatnam, Andhra Pradesh, India.
3P.S.L Krishna Kanth, Department of Electronics and Communication Engineering, Visakhapatnam, Andhra Pradesh, India.
4B.Vinay, Department of Electronics and Communication Engineering, Visakhapatnam, Andhra Pradesh, India.
5V.Nikhil, Department of Electronics and Communication Engineering, Visakhapatnam, Andhra Pradesh, India.
Manuscript received on May 20, 2021. | Revised Manuscript received on May 24, 2021. | Manuscript published on May 30, 2021. | PP: 265-258 | Volume-10 Issue-1, May 2021. | Retrieval Number: 100.1/ijrte.A59430510121 | DOI: 10.35940/ijrte.A5943.0510121
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Removal of noise is the heart for speech and audio signal processing. Impulse noise is one of the most important noise which corrupts different parts in speech and audio signals. To remove this type of noise from speech and audio signals the technique proposed in this work is signal dependent rank order mean (SD-ROM) method in recursive version. This technique is used to replace the impulse noise samples based on the neighbouring samples. It detects the impulse noise samples based on the rank ordered differences with threshold values. This technique doesn’t change the features and tonal quality of signal. Rank ordered differences is used for detecting the impulse noise samples in speech and audio signals. Once the sample is detected as corrupted sample, that sample is replaced with rank ordered mean value and this rank ordered mean value depends on the sliding window size and neighbouring samples. This technique shows good results in terms of signal to noise ratio (SNR) and peak signal to noise ratio (PSNR) when compared with other techniques. It mainly used for removal of impulse noises from speech and audio signals.
Keywords: Impulse Noise, Sliding Window, Rank Ordered Differences, Rank Ordered Mean.