INALI   02622
INSTITUTO NACIONAL DE LIMNOLOGIA
Unidad Ejecutora - UE
congresos y reuniones científicas
Título:
Furnariidae species recognition using speech-related features and machine learning
Autor/es:
SARQUIS, JUAN A. ; LEON, EVELINA J.; LEANDRO V. VIGNOLO; ALBORNOZ, ENRIQUE M.
Reunión:
Jornada; 45 Jornadas Argentinas de Informática; 2016
Resumen:
The automatic classication of calling bird species is importantto achieve more exhaustive environmental monitoring and to managenatural 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 inhabitthe 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-knownclassication techniques: random forest an support vector machines. Theresults are promising, near 86%, and were validated in a cross-validationscheme.