TY - GEN
T1 - Gammatone Wavelet features for sound classification in surveillance applications
AU - Valero, Xavier
AU - Aliás, Francesc
PY - 2012
Y1 - 2012
N2 - Sound can deliver highly informative data about the environment, which can be of particular interest for hometeleassistance and surveillance purposes. In the sound event recognition process, the signal parameterisation is a crucial aspect. In this work, we propose Gammatone-Wavelet features (GTW) by merging Wavelet analysis, which is well-suited to represent the characteristics of surveillance-related sounds, and Gammatone functions, which model the human auditory system. An experimental evaluation that consists of classifying a set of surveillance-related sounds employing Support Vector Machines has been conducted at different SNR conditions. When compared to typical Wavelet analysis with Daubechies mother function (DWC), the GTW features show superior classification accuracy both in noiseless conditions and noisy conditions for almost any SNR level. Finally, it is observed that the combination of DWC and GTW yields the highest classification accuracies.
AB - Sound can deliver highly informative data about the environment, which can be of particular interest for hometeleassistance and surveillance purposes. In the sound event recognition process, the signal parameterisation is a crucial aspect. In this work, we propose Gammatone-Wavelet features (GTW) by merging Wavelet analysis, which is well-suited to represent the characteristics of surveillance-related sounds, and Gammatone functions, which model the human auditory system. An experimental evaluation that consists of classifying a set of surveillance-related sounds employing Support Vector Machines has been conducted at different SNR conditions. When compared to typical Wavelet analysis with Daubechies mother function (DWC), the GTW features show superior classification accuracy both in noiseless conditions and noisy conditions for almost any SNR level. Finally, it is observed that the combination of DWC and GTW yields the highest classification accuracies.
KW - Ambient Assisted Living
KW - Gammatone function
KW - Wavelet analysis
KW - audio classification
KW - audio-based surveillance
KW - feature extraction
UR - http://www.scopus.com/inward/record.url?scp=84869797682&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84869797682
SN - 9781467310680
T3 - European Signal Processing Conference
SP - 1658
EP - 1662
BT - Proceedings of the 20th European Signal Processing Conference, EUSIPCO 2012
T2 - 20th European Signal Processing Conference, EUSIPCO 2012
Y2 - 27 August 2012 through 31 August 2012
ER -