TY - GEN
T1 - Multichannel transient acoustic signal classification using task-driven dictionary with joint sparsity and beamforming
AU - Zhang, Yang
AU - Nasrabadi, Nasser M.
AU - Hasegawa-Johnson, Mark
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/8/4
Y1 - 2015/8/4
N2 - We are interested in a multichannel transient acoustic signal classification task which suffers from additive/convolutionary noise corruption. To address this problem, we propose a double-scheme classifier that takes the advantage of multichannel data to improve noise robustness. Both schemes adopt task-driven dictionary learning as the basic framework, and exploit multichannel data at different levels - scheme 1 imposes joint sparsity constraint while learning the dictionary and classifier; scheme 2 adopts beamforming at signal formation level. In addition, matched filter and robust ceptral coefficients are applied to improve noise robustness of the input feature. Experiments show that the proposed classifier significantly outperforms the baseline algorithms.
AB - We are interested in a multichannel transient acoustic signal classification task which suffers from additive/convolutionary noise corruption. To address this problem, we propose a double-scheme classifier that takes the advantage of multichannel data to improve noise robustness. Both schemes adopt task-driven dictionary learning as the basic framework, and exploit multichannel data at different levels - scheme 1 imposes joint sparsity constraint while learning the dictionary and classifier; scheme 2 adopts beamforming at signal formation level. In addition, matched filter and robust ceptral coefficients are applied to improve noise robustness of the input feature. Experiments show that the proposed classifier significantly outperforms the baseline algorithms.
KW - Transient acoustic signal
KW - beamforming
KW - joint sparsity
KW - multichannel
KW - task-driven dictionary learning
UR - http://www.scopus.com/inward/record.url?scp=84946033747&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84946033747&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2015.7178294
DO - 10.1109/ICASSP.2015.7178294
M3 - Conference contribution
AN - SCOPUS:84946033747
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1866
EP - 1870
BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Y2 - 19 April 2014 through 24 April 2014
ER -