Analyzing bird song syllables on the Self-Organizing Map

In this work, we present two methods for analyzing the syllables of the bird song on the Self-Organizing Map (SOM). Dynamic time warping is used for computing the distances between the data sequences. In the first method, the pairwise distances are first computed between the data sequences and each row of the distance matrix is then considered as a feature vector. The conventional SOM with fixed-dimensional model vectors can then be used. The second method is based on online learning of variablelength sequence prototypes. In both cases the SOM is used for constructing a low-dimensional visualization space for the data. We give results analyzing the syllables from five bird species belonging to the Phylloscopus family of passerine birds.