TY - JOUR AU - Vujnović, Sanja AU - Marjanović, Aleksandra AU - Đurović, Željko PY - 2021/10/22 Y2 - 2024/03/29 TI - ACOUSTIC SIGNAL DENOISING BASED ON ROBUST PRINCIPAL COMPONENT ANALYSIS JF - ETIMA JA - etima VL - 1 IS - 1 SE - Articles DO - UR - https://js.ugd.edu.mk/index.php/etima/article/view/4521 SP - 300-308 AB - AbstractRobust principal component analysis (RPCA) is a powerful procedure which decomposes a matrix into its lowrankand sparse matrix components. As such it can be used for signal denoising in situations where useful part ofthe signal can be represented as a low-rank matrix, which is usually the case in acoustic signals with someinherent periodicity. This paper examines the applicability of RPCA for cyclostationary acoustic signal denoisingby decomposing the Short-time Fourier transform of a signal and eliminating its sparse component. The mainpurpose of this approach is improvement of the signal-to-noise ratio in acoustic signals obtained in noisyindustrial surroundings for the purpose of fault detection or machine state estimation. The procedure is tested onartificially generated signals as well as on real acoustic recordings.Key wordsAcoustic signals, Noise removal, RPCA, Industrial state estimation. ER -