Furnariidae species recognition using speech-related features and machine learning

LEANDRO D. VIGNOLO; JUAN A. SARQUIS; EVELINA LEON; ENRIQUE M. ALBORNOZ

Capital Federal, Buenos Aires

Congreso; XVII Argentine Symposium on Artificial Intelligence (ASAI 2016) - 45th JAIIO; 2016

UNTREF - SADIO

The automatic classification of calling bird species is important 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 automaticsystems can speed up and improve all the process. In this work, we usestate-of-art features designed for speech and speaker state recognitionto classify 25 species of Furnariidae family. Since Furnariidae species in-habit the Litoral Paranaense region of Argentina (South America), thiswork could promote further research on the topic and the implementationof in-situ monitoring systems. Our analysis includes two widely-knownclassification techniques: random forest and support vector machines. Theresults are promising, near 86%, and were validated in a cross-validationscheme.