TY - GEN
T1 - GEOMETRICALLY CONSTRAINED SOURCE EXTRACTION AND DEREVERBERATION BASED ON JOINT OPTIMIZATION
AU - Yang, Yichen
AU - Wang, Xianrui
AU - Brendel, Andreas
AU - Zhang, Wen
AU - Kellermann, Walter
AU - Chen, Jingdong
N1 - Publisher Copyright:
© 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.
PY - 2023
Y1 - 2023
N2 - Source extraction, which aims at extracting the target source signals from the observed reverberant mixtures, plays an important role in voice communication and human-machine interfaces. Among the numerous source extraction methods that have been developed, the geometrically constrained (GC) one, which incorporates the direction-of-arrival (DOA) information of the target signals, has demonstrated great potential. However, this method generally suffers from significant performance degradation in strong reverberant environments since it is challenging to obtain in such environments accurate DOA estimates that are needed by the algorithm. To address this problem, we present in this work an iterative algorithm, which integrates the source-wise weighted prediction error (WPE)based dereverberation principle with the geometrically constrained source extraction method. We show that this algorithm is able to improve the DOA estimation accuracy as well as the source extraction performance.
AB - Source extraction, which aims at extracting the target source signals from the observed reverberant mixtures, plays an important role in voice communication and human-machine interfaces. Among the numerous source extraction methods that have been developed, the geometrically constrained (GC) one, which incorporates the direction-of-arrival (DOA) information of the target signals, has demonstrated great potential. However, this method generally suffers from significant performance degradation in strong reverberant environments since it is challenging to obtain in such environments accurate DOA estimates that are needed by the algorithm. To address this problem, we present in this work an iterative algorithm, which integrates the source-wise weighted prediction error (WPE)based dereverberation principle with the geometrically constrained source extraction method. We show that this algorithm is able to improve the DOA estimation accuracy as well as the source extraction performance.
KW - Blind source separation
KW - dereverberation
KW - geometrical constraint
KW - semi-blind source extraction
UR - http://www.scopus.com/inward/record.url?scp=85178324280&partnerID=8YFLogxK
U2 - 10.23919/EUSIPCO58844.2023.10289750
DO - 10.23919/EUSIPCO58844.2023.10289750
M3 - 会议稿件
AN - SCOPUS:85178324280
T3 - European Signal Processing Conference
SP - 41
EP - 44
BT - 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings
PB - European Signal Processing Conference, EUSIPCO
T2 - 31st European Signal Processing Conference, EUSIPCO 2023
Y2 - 4 September 2023 through 8 September 2023
ER -