Furnariidae species recognition using speech-related features and machine learning

LEANDRO VIGNOLO; SARQUIS JUAN ANDRES; EVELINA LEON; ALBORNOZ MARCELO

Ciudad Autónoma de Buenos Aires

Simposio; ASAI 2016, 17º Simposio Argentino de Inteligencia Artificial; 2016

Universidad de Tres de Febrero. Centro Cultural Borges.

The automatic classification of calling bird species is impor- tant to achieve more exhaustive environmental monitoring and to man- age natural resources. Bird vocalizations allow to recognise new species, their natural history and macro-systematic relations, while automatic systems can speed up and improve all the process. In this work, we use state-of-art features designed for speech and speaker state recognition to classify 25 species of Furnariidae family. Since Furnariidae species in- habit the Litoral Paranaense region of Argentina (South America), this work could promote further research on the topic and the implementation of in-situ monitoring systems. Our analysis includes two widely-known classification techniques: random forest an support vector machines. The results are promising, near 86%, and were validated in a cross-validation scheme.