TY - GEN
T1 - Low-power SVM classifiers for sound event classification on mobile devices
AU - Mak, Man Wai
AU - Kung, Sun Yuan
PY - 2012
Y1 - 2012
N2 - With the high processing power of today's smartphones, it becomes possible to turn a smartphone into a personal audio surveillance and monitoring system. Ideally, such a system should be able to detect and classify a variety of sound events 24 hours a day and trigger an emergence phone call or message once a specified sound event (e.g., screaming) occurs. To prolong battery life, it is important to trade off the detection accuracy against power consumption. This paper investigates the power consumption of different stages of a sound-event classification system, including segmentation, feature extraction, and SVM scoring. The performance and power consumption of various acoustic features and SVM kernels are compared. This paper advocates the notion of intrinsic complexity through which the scoring function of polynomial SVMs can be written in a matrix-vector-multiplication form so that the resulting complexity becomes independent of the number of support vectors. Results show that this intrinsic complexity can reduce the CPU utilization of polynomial SVMs by 28 times without reducing classification accuracy.
AB - With the high processing power of today's smartphones, it becomes possible to turn a smartphone into a personal audio surveillance and monitoring system. Ideally, such a system should be able to detect and classify a variety of sound events 24 hours a day and trigger an emergence phone call or message once a specified sound event (e.g., screaming) occurs. To prolong battery life, it is important to trade off the detection accuracy against power consumption. This paper investigates the power consumption of different stages of a sound-event classification system, including segmentation, feature extraction, and SVM scoring. The performance and power consumption of various acoustic features and SVM kernels are compared. This paper advocates the notion of intrinsic complexity through which the scoring function of polynomial SVMs can be written in a matrix-vector-multiplication form so that the resulting complexity becomes independent of the number of support vectors. Results show that this intrinsic complexity can reduce the CPU utilization of polynomial SVMs by 28 times without reducing classification accuracy.
KW - Low-power SVM
KW - audio surveillance
KW - kernel-energy tradeoff
KW - smartphones
KW - sound event classification
UR - http://www.scopus.com/inward/record.url?scp=84867597425&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867597425&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2012.6288296
DO - 10.1109/ICASSP.2012.6288296
M3 - Conference contribution
AN - SCOPUS:84867597425
SN - 9781467300469
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1985
EP - 1988
BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Y2 - 25 March 2012 through 30 March 2012
ER -