Linear prediction coding analysis and self-organizing feature map as toolsto classify stress calls of domestic pigs (Sus scrofa)

It is assumed that calls may give information about the inner (emotional) s tate of an animal. Hence, in the last years sound analysis has become an in creasingly important tool for the interpretation of the behavior, the healt h condition, and the well-being of animals. A procedure was developed that allows the characterization, classification, and visualization of the clust er structures of stress calls of domestic pigs (Sus scrofa). Based on the a coustic model of the sound production the extraction of features from calls was performed with linear prediction coding (LPC). A vector-based self-org anizing neuronal network was trained with the determined LPC coefficients, resulting in a feature map. The cluster structure of the calls was then vis ualized with a unified matrix and the neurons were labeled for their input origin. The basic applicability of the procedure was tested by using two ex amples which were of special interest for a possible evaluation of the norm al farming practice. The procedure worked well both in discriminating indiv idual piglets by their scream characteristics and in classifying pig stress calls vs other calls and noise occurring under normal farming conditions. (C) 2001 Acoustical Society of America.