Humans benefit considerably from exploiting two ears in everyday listening tasks. It therefore seems to be a promising concept for machine listening approaches to emulate the biological mechanisms of binaural signal processing before applying methods of artificial intelligence. In this work we employ a cross-correlation-based auditory model to automatically perform classification tasks on elementary everyday sound events. We present a heuristic scheme to extract the relevant features from the model’s output data. Given a set of training data, a classifier is then constructed using support vector machine (SVM) learning. The proposed method is validated in classification experiments performed on a database of natural sounds. We further discuss its robustness against variation of room acoustics.
[1]
Morten Løve Jepsen,et al.
Towards a binaural modelling toolbox
,
2011
.
[2]
Yi-Min Huang,et al.
Weighted support vector machine for classification with uneven training class sizes
,
2005,
2005 International Conference on Machine Learning and Cybernetics.
[3]
W. Lindemann.
Extension of a binaural cross-correlation model by contralateral inhibition. I. Simulation of lateralization for stationary signals.
,
1986,
The Journal of the Acoustical Society of America.
[4]
Chih-Jen Lin,et al.
LIBSVM: A library for support vector machines
,
2011,
TIST.
[5]
Klaus Obermayer,et al.
Representations and Predictors for Everyday Sounds
,
2008
.