| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0396302 |
| utime |
20240111140835.0 |
| mtime |
20130926235959.9 |
| title
(primary) (eng) |
Informed generalized sidelobe canceler utilizing sparsity of speech signals |
| specification |
| page_count |
6 s. |
| media_type |
C |
|
| serial |
| ARLID |
cav_un_epca*0396301 |
| ISBN |
978-1-4799-1178-3 |
| title
|
Proceedings of MLSP2013 |
| publisher |
| place |
Piscataway, USA |
| name |
IEEE |
| year |
2013 |
|
|
| keyword |
noise extraction |
| keyword |
speech enhancement |
| keyword |
generalized sidelobe canceler |
| author
(primary) |
| ARLID |
cav_un_auth*0050739 |
| name1 |
Málek |
| name2 |
J. |
| country |
CZ |
|
| author
|
| ARLID |
cav_un_auth*0108100 |
| name1 |
Koldovský |
| name2 |
Zbyněk |
| full_dept (cz) |
Stochastická informatika |
| full_dept |
Department of Stochastic Informatics |
| department (cz) |
SI |
| department |
SI |
| institution |
UTIA-B |
| full_dept |
Department of Stochastic Informatics |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0294189 |
| name1 |
Gannot |
| name2 |
S. |
| country |
IL |
|
| author
|
| ARLID |
cav_un_auth*0101212 |
| name1 |
Tichavský |
| name2 |
Petr |
| full_dept (cz) |
Stochastická informatika |
| full_dept |
Department of Stochastic Informatics |
| department (cz) |
SI |
| department |
SI |
| institution |
UTIA-B |
| full_dept |
Department of Stochastic Informatics |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| project_id |
GAP103/11/1947 |
| agency |
GA ČR |
| country |
CZ |
| ARLID |
cav_un_auth*0301478 |
|
| abstract
(eng) |
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. |
| action |
| name |
IEEE International Workshop on Machine Learning for Signal Processing |
| place |
Southampton |
| dates |
22.09.2013-25.09.2013 |
| country |
GB |
| ARLID |
cav_un_auth*0294180 |
|
| reportyear |
2014 |
| RIV |
BI |
| num_of_auth |
4 |
| presentation_type |
PR |
| permalink |
http://hdl.handle.net/11104/0224135 |
| mrcbC61 |
1 |
| arlyear |
2013 |
| mrcbU56 |
149kB |
| mrcbU63 |
cav_un_epca*0396301 Proceedings of MLSP2013 978-1-4799-1178-3 Piscataway, USA IEEE 2013 |
|