Bird Voice Classification Based on Combination Feature Extraction and Reduction Dimension with the K-Nearest Neighbor

Abstract

Indonesia is rich in flora and fauna diversity, but it is experiencing an increasing number of endangered populations. The public can prevent the expanding population threatened with extinction by knowing the types of fauna, especially birds threatened with extinction. This study proposes an automatic grouping method to recognize bird sound patterns in an open environment. This experiment used bird data from a public dataset and obtained bird sound patterns by recording from a distance far enough to make sounds without feeling disturbed freely. However, the sound of birds may contain noise and need data processing using YAMME to be carried out the noise, and birds’ voices can be separated. After that, the data was extracted using the combination of Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) methods also reduced the dimensions of the feature before completing the identification. The bird identification obtained provides an accuracy performance that reaches 78.11%, and these results are higher than other feature extraction methods that also apply dimensional reduction.