Robust cepstral feature for bird sound classification

Birds are excellent environmental indicators and may indicate sustainability of the ecosystem; birds be used to provide provisioning, regulating, supporting services. Therefore, birdlife conservation-related researches always receive centre stage. Due airborne nature dense tropical forest, bird identifications through audio a better solution than visual identification. The goal this study is find most appropriate cepstral features that can classify sounds more accurately. Fifteen (15) endemic Bornean have been selected segmented using an automated energy-based algorithm. Three (3) types extracted; linear prediction cepstrum coefficients (LPCC), mel frequency (MFCC), gammatone (GTCC), separately for classification purposes support vector machine (SVM). Through comparison between their results, it has demonstrated model utilising GTCC features, with 93.3% accuracy, outperforms models MFCC LPCC features. This demonstrates robustness classification. result significant advancement sound research, which shown many applications such as in eco-tourism wildlife management.