Das Zoologische Forschungsmuseum Alexander Koenig

ist ein Forschungsmuseum der Leibniz Gemeinschaft

robust acoustic recognition of birds

AutorInnen: 
Mporas, I., Ganchev, T., Kocsis, O., Fakotakis, N., Jahn, O., Riede, K.
Erscheinungsjahr: 
2013
Vollständiger Titel: 
Integration of temporal contextual information for robust acoustic recognition of bird species from real-field data.
Autor/-innen des ZFMK: 
Org. Einordnung: 
Publiziert in: 
I.J. Intelligent Systems and Applications
Publikationstyp: 
Zeitschriftenaufsatz
DOI Name: 
doi:10.5815/ijisa.2013.07.02
Bibliographische Angaben: 
Mporas, I., Ganchev, T., Kocsis, O., Fakotakis, N., Jahn, O., Riede, K. (2013): Integration of temporal contextual information for robust acoustic recognition of bird species from real-field data. I.J. Intelligent Systems and Applications 7: 9-15. doi: 10.5815/ijisa.2013.07.02
Abstract: 

We report on the development of an automated acoustic bird recognizer with improved noise robustness, which is part of a long-term project, aiming at the establishment of an automated biodiversity monitoring system at the Hymettus Mountain near Athens, Greece. In particular, a typical audio processing strategy, which has been proved quite successful in various audio recognition applications, was amended with a simple and effective mechanism for integration of temporal contextual information in the decision-making process. In the present implementation, we consider integration of temporal contextual information by joint post-processing of the recognition results for a number of preceding and subsequent audio frames. In order to evaluate the usefulness of the proposed scheme on the task of acoustic bird recognition, we experimented with six widely used classifiers and a set of real-field audio recordings for two bird species which are present at the Hymettus Mountain. The highest achieved recognition accuracy obtained on the real-field data was approximately 93%, while experiments with additive noise showed significant robustness in low signal-to-noise ratio setups. In all cases, the integration of temporal contextual information was found to improve the overall accuracy of the recognizer.