0531483 20240103224313.620200810235959.9 85089296542 000556759700004 10.1109/TSP.2020.3009507 10 s. P cav_un_epca*02567271053-587X681 (2020)4258-4267 Blind source separation independent component/vector analysis Cramér-Rao lower bound, cav_un_auth*0350114 Kautský V. CZ 60 cav_un_auth*0101212 Tichavský Petr UTIA-B Stochastická informatika Department of Stochastic Informatics SI SI Department of Stochastic Informatics 15 Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0230113 Koldovský Z. CZ 15 cav_un_auth*0394533 Adali T. US 10 http://library.utia.cas.cz/separaty/2020/SI/tichavsky-0531483.pdf https://ieeexplore.ieee.org/document/9141450 GA17-00902S GA ČR cav_un_auth*0345929 GA20-17720S GA ČR CZ cav_un_auth*0395418 Independent Vector Analysis (IVA) is a method for joint Blind Source Separation of multiple datasets with wide area of applications including audio source separation, biomedical data analysis, etc. In this paper, identification conditions and Cramér-Rao Lower Bound (CRLB) on the achievable accuracy are derived for the complex-valued case involving circular and non-circular signals and correlated and uncorrelated datasets.The identification conditions describe when independent sources can be separated from their linear mixture in the statistically consistent manner. The CRLB shows how non-Gaussianty, non-circularity of sources and statistical dependence between datasets influence the attainable separation accuracy. Examples presented in the experimental part confirm the validity of the CRLB. Also, they show certain gap between the attainable accuracy and performance of state-of-the-art algorithms,especially, in case of highlynon-circular signals. Hence, there is a room for possible improvements. WOS JD 20000 20200 20201 2021 4 RVO:67985556 http://hdl.handle.net/11104/0310654 S 3+4 Article Engineering Electrical Electronic C ENGINEERING.ELECTRICAL&ELECTRONIC 5.239 0.767 9.1 0.04146 1.701 39639 314 1.638 45.4 6.24 9132 Q1 4.333 468 Q1 91.464 85.2 Q1* Q1* 1.6 Q1 85.165 2020 85089296542 SCOPUS PUBMED 000556759700004 WOS cav_un_epca*0256727 IEEE Transactions on Signal Processing 1053-587X 1941-0476 Roč. 68 č. 1 2020 4258 4267