0396302 20240111140835.020130926235959.9 6 s. C cav_un_epca*0396301978-1-4799-1178-3Piscataway, USAIEEE2013 noise extraction speech enhancement generalized sidelobe canceler cav_un_auth*0050739 Málek J. CZ cav_un_auth*0108100 Koldovský Zbyněk Stochastická informatika Department of Stochastic Informatics SI SI UTIA-B Department of Stochastic Informatics Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0294189 Gannot S. IL cav_un_auth*0101212 Tichavský Petr Stochastická informatika Department of Stochastic Informatics SI SI UTIA-B Department of Stochastic Informatics Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2013/SI/tichavsky-informed generalized sidelobe canceler utilizing sparsity of speech signals.pdf 149kB GAP103/11/1947 GA ČR CZ cav_un_auth*0301478 This report proposes a novel variant of the generalized sidelobe canceler. It assumes that a set of prepared relative transfer functions (RTFs) is available for several potential positions of a target source within a confined area. The key problem here is to select the correct RTF at any time, even when the exact position of the target is unknown and interfering sources are present. We propose to select the RTF based on l_p-norm, p ≤ 1, measured at the blocking matrix output in the frequency domain. Subsequent experiments show that this approach significantly outperforms previously proposed methods for selection when the target and interferer signals are speech signals. IEEE International Workshop on Machine Learning for Signal Processing Southampton 22.09.2013-25.09.2013 GB cav_un_auth*0294180 2014 BI 4 PR http://hdl.handle.net/11104/0224135 1 2013 149kB cav_un_epca*0396301 Proceedings of MLSP2013 978-1-4799-1178-3 Piscataway, USA IEEE 2013