ANALISA ALGORITMA CONVOLUTION NEURAL NETWORK (CNN) PADA KLASIFIKASI GENRE MUSIK BERDASAR DURASI WAKTU
Abstract
Genre musik pada umumnya digolongkan berdasarkan kemiripan ritmik, frekuensi dan harmoni. Biasanya masyarakat memilih genre musik sesuai kesenangan mereka. Pada penelitian ini, algoritma Convolutional Neural Network (CNN) digunakan untuk klasifikasi genre musik. Ekstraksi fitur yang digunakan antara lain: Chroma stft, Spectral centroid, Spectral bandwidth, Spectral Rolloff , Root Mean Square Energy (RMSE), Zero_Crossing Rate, Mel-Frequency Cepstral Coefficients, Harmony, Tempo, dan Perceptron. Perbedaan durasi waktu musik pada data uji coba adalah 10 detik dan 30 detik. Hasil uji coba pada data durasi 10 detik menghasilkan akurasi prediksi yaitu sebesar 81%. Sedangkan hasil uji coba pada data durasi 30 detik menghasilkan akurasi prediksi yaitu sebesar 58%. Hal ini dapat disimpulkan bahwa klasifikasi genre musik dengan durasi waktu yang lebih pendek ternyata mampu menghasilkan nilai akurasi yang lebih baik.
References
G. Tzanetakis, P. Cook, Musical genre classification of audio signals, IEEE Trans. Speech Audio Process. 10 (5) (2002) 293–302.
G. Marques, T. Langlois, F. Gouyon, M. Lopes, M. Sordo, Short-term feature space and music genre classification, J. New Music Res. 40 (2011) 127–137.
C.M. Yeh, L. Su, Y. Yang, Dual-layer bag-of-frames model for music genre classification, in: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, pp. 246–250.
S. Shin, H. Yun, W. Jang, H. Park, Extraction of acoustic features based on auditory spike code and its application to music genre classification, IET Signal Process. 13 (2) (2019) 230–234.
Y. Yu, S. Luo, S. Liu, H. Qiao, Y. Liu, L. Feng, Deep attention based music genre classification, Neurocomputing.
T. Kobayashi, A. Kubota, Y. Suzuki, Audio feature extraction based on sub-band signal correlations for music genre classification, in: 2018 IEEE International Symposium on Multimedia, ISM, 2018, pp. 180–181.
Y. Panagakis, C. Kotropoulos, G.R. Arce, Music genre classification via sparse representations of auditory temporal modulations, in: 2009 17th European Signal Processing Conference, 2009, pp. 1–5.
Y.M. Costa, L.S. Oliveira, C.N. Silla, An evaluation of convolutional neural networks for music classification using spectrograms, Appl. Soft Comput. 52 (2017) 28–38.
H. Yang, W.-Q. Zhang, Music genre classification using duplicated convolutional layers in neural networks, in: INTERSPEECH 2019, 2019.
C. Senac, T. Pellegrini, F. Mouret, J. Pinquier, Music feature maps with convolutional neural networks for music genre classification, in: Proceed- ings of the 15th International Workshop on Content-Based Multimedia Indexing, CBMI ’17, ACM, New York, NY, USA, 2017, pp. 19:1–19:5.
B.L. Sturm, The gtzan dataset: Its contents, its faults, their effects on evaluation, and its future use, arXiv preprint arXiv:1306.1461.
Full Text: PDF
Refbacks
- There are currently no refbacks.
