0563805 20230323095823.120221109235959.9 85141497959 000880643100006 10.1109/TSP.2022.3216106 15 s. P cav_un_epca*02567271053-587X701 (2022)5102-5116 blind source extraction non-stationarity speech processing cav_un_auth*0230113 Koldovský Z. CZ cav_un_auth*0350114 Kautský V. CZ cav_un_auth*0101212 Tichavský Petr UTIA-B Stochastická informatika Department of Stochastic Informatics SI SI Department of Stochastic Informatics Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2022/SI/tichavsky-0563805.pdf https://ieeexplore.ieee.org/document/9927365 GA20-17720S GA ČR CZ cav_un_auth*0395418 In this article, nonstationary mixing and source models are combined for developing new fast and accurate algorithms for Independent Component or Vector Extraction (ICE/IVE), one of which stands for a new extension of the well-known FastICA. This model allows for a moving source-of-interest (SOI) whose distribution on short intervals can be (non-)circular (non-)Gaussian. A particular Gaussian source model assuming tridiagonal covariance matrix structures is proposed. It is shown to be beneficial in the frequency-domain speaker extraction problem. The algorithms are verified in simulations. In comparison to the state-of-the-art algorithms, they show superior performance in terms of convergence speed and extraction accuracy. WOS BB 20000 20200 20201 2023 3 RVO:67985556 https://hdl.handle.net/11104/0336407 S 3+4 Article Engineering Electrical Electronic C ENGINEERING.ELECTRICAL&ELECTRONIC 6 1 9.1 0.03934 1.942 44220 2.503 4.900 443 Q1 78 Q1 Q1* 1.29 Q1 78 2022 85141497959 SCOPUS PUBMED 000880643100006 WOS cav_un_epca*0256727 IEEE Transactions on Signal Processing 1053-587X 1941-0476 Roč. 70 č. 1 2022 5102 5116