TY - GEN
T1 - Robust multi-feature segmentation and indexing for natural sound environments
AU - Wichern, Gordon
AU - Thornburg, Harvey
AU - Mechtley, Brandon
AU - Fink, Alex
AU - Tu, Kai
AU - Spanias, Andreas
PY - 2007
Y1 - 2007
N2 - Creating an audio database from continuous long-term recordings, allows for sounds to not only be linked by the time and place in which they were recorded, but also to sounds with similar acoustic characteristics. Of paramount importance in this application is the accurate segmentation of sound events, enabling realistic navigation of these recordings. We first propose a novel feature set of specific relevance to environmental sounds, and then develop a Bayesian framework for sound segmentation, which fuses dynamics across multiple features. This probabilistic model possesses the ability to account for non-instantaneous sound onsets and absent or delayed responses among individual features, providing flexibility in defining exactly what constitutes a sound event. Example recordings demonstrate the diversity of our feature set, and the utility of our probabilistic segmentation model in extracting sound events from both indoor and outdoor environments.
AB - Creating an audio database from continuous long-term recordings, allows for sounds to not only be linked by the time and place in which they were recorded, but also to sounds with similar acoustic characteristics. Of paramount importance in this application is the accurate segmentation of sound events, enabling realistic navigation of these recordings. We first propose a novel feature set of specific relevance to environmental sounds, and then develop a Bayesian framework for sound segmentation, which fuses dynamics across multiple features. This probabilistic model possesses the ability to account for non-instantaneous sound onsets and absent or delayed responses among individual features, providing flexibility in defining exactly what constitutes a sound event. Example recordings demonstrate the diversity of our feature set, and the utility of our probabilistic segmentation model in extracting sound events from both indoor and outdoor environments.
UR - http://www.scopus.com/inward/record.url?scp=46749124289&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=46749124289&partnerID=8YFLogxK
U2 - 10.1109/CBMI.2007.385394
DO - 10.1109/CBMI.2007.385394
M3 - Conference contribution
AN - SCOPUS:46749124289
SN - 1424410118
SN - 9781424410118
T3 - CBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing, Proceedings
SP - 69
EP - 76
BT - CBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing, Proceedings
T2 - CBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing
Y2 - 25 June 2007 through 27 June 2007
ER -