Multiple Classifier Systems for the Recognition of Orthoptera Songs

The classification of bioacoustic time series is topic of this paper. In particular, we discuss the combination of local classifier decisions from several feature spaces with static and adaptable fusion schemes, e.g. averaging, voting and decision templates. We present static fusion schemes and algorithms to calculate decision templates, and demonstrate the behaviour of both approaches to bioacoustic applications, the classification of insect songs. Results of these algorithms are presented for species of crickets and katydids. Both families are members of the insect order Orthoptera.