CLASSIFICATION OF HUMAN AND AI-GENERATED INDONESIAN POP SONGS BASED ON SPECTROGRAM USING CONVOLUTIONAL NEURAL NETWORK

Faris Nur Tsani; Wahyu Syaifullah Jauharis Saputra; Alfan Rizaldy Pratama

doi:10.24252/instek.v11i1.65432

Authors

Faris Nur Tsani UPN Veteran Jawa Timur
Wahyu Syaifullah Jauharis Saputra UPN Veteran Jawa Timur
Alfan Rizaldy Pratama UPN Veteran Jawa Timur

DOI:

https://doi.org/10.24252/instek.v11i1.65432

Keywords:

AI-Generated Music, Convolutional Neural Network, Klasifikasi Audio, Lagu Pop Indonesia, STFT Spektogram

Abstract

Pesatnya perkembangan teknologi kecerdasan buatan (AI) memicu lonjakan produksi lagu generatif yang menyerupai karya manusia, sehingga menghadirkan tantangan signifikan terhadap orisinalitas dan hak cipta musik. Penelitian ini bertujuan mengklasifikasikan lagu Pop Indonesia kategori human-generated dan AI-generated menggunakan pendekatan Convolutional Neural Network (CNN) berbasis arsitektur ResNet-18. Dataset terdiri dari 100 lagu berformat MP3 yang terbagi seimbang antara karya manusia dan karya AI dari platform Suno dan Udio. Data audio diproses melalui teknik segmentasi overlapping window berdurasi 10 detik dengan overlap 5 detik, kemudian diekstraksi menjadi citra spektrogram Short-Time Fourier Transform (STFT). Total data yang dihasilkan mencapai 4.282 segmen audio. Hasil pelatihan selama 100 epoch menunjukkan bahwa model mencapai konvergensi dengan train accuracy 100% dan validation accuracy 95,09%. Pada tahap pengujian menggunakan data yang belum pernah dilihat sebelumnya, model menunjukkan performa unggul dengan tingkat akurasi 93,01%. Temuan ini mengonfirmasi bahwa penggunaan representasi spektogram dalam arsitektur CNN mampu menangkap perbedaan fitur frekuensi dan temporal secara efektif untuk mengidentifikasi musik berbasis AI pada genre Pop Indonesia.

Downloads

Download data is not yet available.

References

[1] T. Ingham, “Nearly a third of all tracks uploaded to Deezer are now fully AI-generated,” Music Business Worldwide. Accessed: Nov. 10, 2025. [Online]. Available: https://www.musicbusinessworldwide.com/nearly-a-third-of-all-tracks-uploaded-to-deezer-are-now-fully-ai-generated-says-platform/

[2] E. Darlene, “Identitas Kultural Musik Pop Indonesia dalam Konteks Seni Urban,” Tonika J. Penelit. Dan Pengkaj. Seni, vol. 7, no. 1, pp. 49–61, May 2024, doi: 10.37368/tonika.v7i1.573.

[3] L. Bigo and M. Andreatta, “A GEOMETRIC MODEL FOR THE ANALYSIS OF POP MUSIC,” no. Sonus-special issue on modelling in musical analysis, pp. 36–48, 2014.

[4] L. A. Chanan, “Analisis prinsip penggunaan wajar (Fair Use) pada lagu buatan AI di Platform Spotify berdasarkan Undang-Undang Nomor 28 Tahun 2014 tentang Hak Cipta,” undergraduate, Universitas Islam Negeri Maulana Malik Ibrahim, 2025. Accessed: Dec. 15, 2025. [Online]. Available: http://etheses.uin-malang.ac.id/74572/

[5] D. Afchar, G. Meseguer-Brocal, and R. Hennequin, “AI-Generated Music Detection and its Challenges,” in ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India: IEEE, Apr. 2025, pp. 1–5. doi: 10.1109/ICASSP49660.2025.10890655.

[6] A. Parlys, A. A. Zahra, and A. Hidayatno, “PENGGOLONGAN LAGU BERDASARKAN SPEKTOGRAM DENGAN CONVOLUTION NEURAL NETWORK,” Transient J. Ilm. Tek. Elektro, vol. 7, no. 1, pp. 28–33, Mar. 2018, doi: 10.14710/transient.v7i1.28-33.

[7] S. N. Utama, J. E. W. Prakasa, and W. Hariyanto, “Klasifikasi Irama Bacaan Al-Qur’an Menggunakan Algoritma CNN,” vol. 7, no. 1, 2025.

[8] S. Ghosh, A. Ghosh, M. Bhutiani, and G. P. Mondal, “Interpretable Deep Learning for Music Genre Classification Using Spectrogram Analysis,” in 2025 International Conference on Computing, Intelligence, and Application (CIACON), Durgapur, India: IEEE, Jul. 2025, pp. 1–6. doi: 10.1109/CIACON65473.2025.11189702.

[9] K. Choi, G. Fazekas, M. Sandler, and K. Cho, “Convolutional recurrent neural networks for music classification,” in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar. 2017, pp. 2392–2396. doi: 10.1109/ICASSP.2017.7952585.

[10] S. Dieleman and B. Schrauwen, “End-to-end learning for music audio,” in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy: IEEE, May 2014, pp. 6964–6968. doi: 10.1109/ICASSP.2014.6854950.

[11] J. Wilson, A. Rao, and A. Taranum, “An Enhanced CNN Architecture for Music Genre Classification on the GTZAN Dataset,” 2025 Third Int. Conf. Netw. Multimed. Inf. Technol. NMITCON, pp. 01–08, Oct. 2025, doi: DOI:%2010.1109/NMITCON65824.2025.11188194.

[12] Y. Li, Q. Sun, H. Li, L. Specia, and B. W. Schuller, “Explainable detection of machine generated music and early systematic evaluation,” vol. Article number: 13757 (2026), Apr. 2026, doi: https://doi.org/10.1038/s41598-026-42133-7.

[13] M. Ashraf, F. Abid, M. O. Raza, J. Rasheed, S. Alsubai, and T. Asuroglu, “Music genre classification with modified residual learning and dual neural network,” PLOS One, vol. 20, no. 10, p. e0333808, Oct. 2025, doi: 10.1371/journal.pone.0333808.

[14] A. Rojas, G. J. Dolecek, J. M. De La Rosa, and G. Liñán-Cembrano, “Increasing the Accuracy of Spectrogram-based Spectrum Sensing Trained by a Deep Learning Network Using a Resnet-18 Model,” in 2024 39th Conference on Design of Circuits and Integrated Systems (DCIS), Catania, Italy: IEEE, Nov. 2024, pp. 1–4. doi: 10.1109/DCIS62603.2024.10769191.

[15] Z. Chen, H. Wang, C.-H. Yeh, and X. Liu, “Classify Respiratory Abnormality in Lung Sounds Using STFT and a Fine-Tuned ResNet18 Network,” in 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS), Taipei, Taiwan: IEEE, Oct. 2022, pp. 233–237. doi: 10.1109/BioCAS54905.2022.9948614.

[16] T. Virtanen, M. D. Plumbley, and D. Ellis, Eds., Computational Analysis of Sound Scenes and Events. Cham: Springer International Publishing, 2018. doi: 10.1007/978-3-319-63450-0.

[17] G. Tzanetakis and P. Cook, “Musical genre classification of audio signals,” IEEE Trans. Speech Audio Process., vol. 10, no. 5, pp. 293–302, Jul. 2002, doi: 10.1109/TSA.2002.800560.

[18] A. H. Prawironegoro and B. H. Prasetio, “PENERAPAN SHORT TIME FOURIER TRANSFORM PADA KOEFISIEN CEPSTRAL MEL UNTUK MENGHITUNG JUMLAH PEMBICARA,” J. Pengemb. Teknol. Inf. Dan Ilmu Komput., vol. 1, no. 1, Jan. 2017.

[19] R. A. N. Diaz, N. L. G. P. Suwirmayanti, and K. Budiarta, “PERBANDINGAN KUALITAS PENGENALAN SUARA UNTUK EKSTRAKSI FITUR MENGGUNAKAN MFCC DAN SPECTRAL,” Naratif J. Nas. Ris. Apl. Dan Tek. Inform., vol. 6, no. 1, pp. 58–63, Jul. 2024, doi: 10.53580/naratif.v6i1.281.

[20] S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Proc. 32nd Int. Conf. Mach. Learn. PMLR 37448-456 2015, vol. 37, pp. 448–456, Jun. 2015.

[21] M. Arsal, B. Agus Wardijono, and D. Anggraini, “Face Recognition Untuk Akses Pegawai Bank Menggunakan Deep Learning Dengan Metode CNN,” J. Nas. Teknol. Dan Sist. Inf., vol. 6, no. 1, pp. 55–63, Jun. 2020, doi: 10.25077/TEKNOSI.v6i1.2020.55-63.

[22] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA: IEEE, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.

[23] I. Markoulidakis and G. Markoulidakis, “Probabilistic Confusion Matrix: A Novel Method for Machine Learning Algorithm Generalized Performance Analysis,” Technologies, vol. 12, no. 7, p. 113, Jul. 2024, doi: 10.3390/technologies12070113.

[24] L. C. Vila, B. L. T. Sturm, L. Casini, and D. Dalmazzo, “The AI Music Arms Race: On the Detection of AI-Generated Music,” vol. 8(1), pp. 179–194, June 25, doi: DOI:%20https://doi.org/10.5334/tis%20mir.254.