Pattern Recognition Bird Sounds Based on Their Type Using Discreate Cosine Transform (DCT) and Gaussian Methods

Abstract

To know the type of bird, most people know from the shape of bird species and the sound of birds. In this study, it identified the pattern of bird sounds. The bird sounds studied were Canary Trills, Vulture and Crow birds. In the introduction of the type of bird sound pattern in this study using the Discrete Cosine Transform (DCT) method and Gaussian value. The researcher conducted several steps to get the sound model of birds, among others, namely (1) bird sound input in the form of WAV file, (2) Hamming Windowing, (3) DFT / FFT, (4) Mel Bank Filter, (5) DCT, and (6) Value Gaussian. The output obtained is in the form of vector values and represented in graphical form. The results obtained in the study of pattern recognition of bird sound types get the results of observations in the same bird sound duration and frequency of the same, then the same pattern is obtained in the same bird as evidenced by calculating the closest distance value with Bray Curtis method. For the same duration of time and the length of the frequency that is not the same; it found that the pattern of bird sounds is not the same.