Acoustic event detection has been an active researchtopic during last few years. However, building an acous-tic event detection system still remains a challengingtask. The difficulty stems from the large intra-class vari-ations in terms of different temporal scales and sounds,non-stationary background noise, and, especially, the na-ture of overlapping events.Several works attempted to address the problem. In gen-eral, these employ simple frame-level presentations and avariety of classification algorithms. Typically, individualevents are modelled as Hidden Markov Models (HMM),and a speech recognition framework is employed to detectthem . The audio segments can also be characterizedby the Gaussian population histograms derived from aGaussian Mixture Model (GMM), and the detection isperformed as classification task using GMMs . In an-other work, Support Vector Machines (SVM) are directlyused over feature vectors derived from audio signals .In this work we introduce a novel concept ofacoustic su-perframeand how event detection can be accomplishedby recognition of superframes using a simple but efficientclass-specific voting scheme. We employrandom forest to model the event superframes. After detection of in-dividual event superframes, the detection hypotheses forthe events will correspond to majority voting from all su-perframes. The evaluation on the UPC-TALP databasefrom CLEAR 2006 challenge  shows that our approachoutperforms the best system submitted to that challenge.
|Number of pages||2|
|Publication status||Published - 01.03.2014|
|Event||40th Annual German Congress on Acoustics - Oldenburg, Germany|
Duration: 10.03.2014 → 13.03.2014
|Conference||40th Annual German Congress on Acoustics|
|Abbreviated title||DAGA 2014|
|Period||10.03.14 → 13.03.14|