Multi Band Spectral Subtraction Combined with Adaptive Noise Estimation
P. Sunitha1, K. Satya Prasad2
1P. Sunitha, Research Scholar with the Department of E.C.E, JNTU, Kakinada, India.
2K. Satya Prasad, Department of Electronics and Communication Engineering JNTU College of Engineering, Anantapur, India.
Manuscript received on 12 March 2019 | Revised Manuscript received on 19 March 2019 | Manuscript published on 30 July 2019 | PP: 2522-2528 | Volume-8 Issue-2, July 2019 | Retrieval Number: B1472078219/19©BEIESP | DOI: 10.35940/ijrte.B1472.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Speech enhancement is a prerequisite for many speech communication applications like speech coders, hearing aids, voice recognition systems, Man –Machine communication, Video conferencing etc. For all these practical systems inputs is a noisy speech, so it requires a pre-processing operation for further processing. This paper gives a method to improve the speech quality in presence of background noise, based on Multi Band Spectral Subtraction combined with adaptive noise estimation. Further the performance analysis of this method is done using objective quality measures like Segmental SNR(seg -SNR), Weighted Slope Spectral Distance (WSSD), Log Likelihood Ratio (LLR), Perceptual Evaluation of Speech Quality (PESQ) and Composite Measures under highly non-stationary noise. Finally, the results were compared against Spectral Subtraction (SS), Multi Band Spectral Subtraction (MBSS) methods and the results shows that the proposed method shows consistence performance against all the cases considered.
Index Terms: Speech Enhancement, Voice Activity Detection, Noise Estimation, Multi Band Spectral Subtraction, Adaptive Noise Estimation, Speech Presence Probability, Objective Performance Measures.
Scope of the Article: High Performance Computing