AUTOMATIC CHORUS DETECTION FOR INDONESIAN MUSIC USING REFRAIN DETECTING METHOD (REFRAID)

Ichsan Permana Putra; Elvia  Budianita; Febi  Yanto; Yusra Yusra

doi:10.20884/1.jutif.2022.3.4.259

Ichsan Permana Putra Teknik Informatika, Universitas Islam Negeri Sultan Syarif Kasim Riau, Indonesia
Elvia Budianita Teknik Informatika, Universitas Islam Negeri Sultan Syarif Kasim Riau, Indonesia
Febi Yanto Teknik Informatika, Universitas Islam Negeri Sultan Syarif Kasim Riau, Indonesia
Yusra Teknik Informatika, Universitas Islam Negeri Sultan Syarif Kasim Riau, Indonesia

DOI: https://doi.org/10.20884/1.jutif.2022.3.4.259

Keywords: Chorus, Dangdut Music, Music, Music Information Retrieval, Pop Music, Refrain Detecting Method

Abstract

Music has become an important part of human life, chorus is part of the musical structure that makes some impression on music, people are generally very familiar with the chorus in music because the chorus is often repeated on music. Automatic chorus detection is a part of Music Information Retrieval which is considered important for building music analysis system with human-like patterns. Refrain Detecting Method (RefraiD) select the chorus by grouping various repeating parts of the music, evaluating the intensity level of the melody from each group, then selecting the group with the highest melodic intensity as the chorus. This paper intends to implement RefraiD in Indonesian pop and dangdut music by downloading 20 pop music videos and 20 dangdut music videos from YouTube then process it with Information retrieval using Python. The results of this paper indicate that the RefraiD method can be used to detect the chorus on Indonesian music with F measure of 91.8% for dangdut music and 91.5% for pop music.

Downloads

Download data is not yet available.

References

G. Agustiningsih, “Konstruksi Gaya Hidup Melalui Musik sebagai Produk Budaya Populer,” J. Komun. dan Bisnis, vol. 6, no. 2, pp. 16–22, 2018.

I. P. Wulandari, “Jatung Utang Sebagai Pengiring Tari Hudog Pada Masyarakat Suku Dayak Kenyah di Desa Sungai Payang Kecamatan Loa Kulu Kabupaten Kutai Kartanegara Kalimantan Timur,” Selonding, vol. 12, no. 12, pp. 1824–1839, 2017, doi: 10.24821/selonding.v12i12.2931.

K. Xu, “Formation and Training of Mass Chorus Team,” Int. Core J. Eng., vol. 7, p. 2021, doi: 10.6919/ICJE.202108_7(8).0026.

Y. Huang, S. Chou, and Y. Yang, “Pop Music Highlighter : Marking the Emotion Keypoints,” vol. 1, pp. 68–78, 2018.

D. Octavia Kumalasari, L. Novamizanti, and I. Nyoman Apraz Ramatryana, “Penentuan lokasi chorus pada musik mp3 menggunakan koefiesien korelasi 2-d pada frame berbasis ciri mel-frequency cepstral coeffisient (mfcc),” 2019.

N. Kroher and J.-M. Díaz-Báñez, “Flamenco Music Information Retrieval Automatic Content-Based Description of Flamenco Music Collections,” 2018.

S. Kurniawan and S. Agustian, “Music Information Retrieval Menggunakan k-NN dan Cosine Similarity,” Semin. Nas. Teknol. Informasi, Komun. dan Ind. 13 , Fak. Sains dan Teknol. UIN Sultan Syarif Kasim Riau, no. November, pp. 94–101, 2021.

and Y. W. Ju-Chiang Wang, Jordan B.L. Smith, Jitong Chen, Xuchen Song, “Supervised Chorus Detection For Popular Music Using Convolutional Neural Network And Multi-Task Learning,” pp. 566–570, 2021.

K. Watanabe and M. Goto, “A Chorus-Section Detection Method For Lyrics Text,” 2020. [Online]. Available: http://www.speech.cs.cmu.edu/cgi-bin/cmudict.

M. Wahyu Setiawan, L. Novamizanti, and I. N. Apraz Ramatryana, “Pemisahan Chorus Pada Music Mp3 Menggunakan Koefisien Korelasi 2-D Berbasis Discrete Cosine Transform (Dct) Dan K-Nearest Neighbor (K-Nn) Separation Of Chorus On Mp3 Music Using 2-D Correlation Coefficient Based On Discrete Cosine Transform (Dct) And K-Nearest Neighbor (K-Nn),” 2019.

B. Adam, I. R. Magdalena, I. Nyoman, and A. Ramatryana, “Perancangan Dan Simulasi Pemisahan Reff Lagu Dengan Metode Discrete Cosine Transform (Dct) Design And Simulation Of Separating The Chorus Songs By Using Discrete Cosine Transform (Dct),” 2018.

N. Ono, S. Tsuchiya, S. Nakamura, and T. Yamamoto, “A Study of the Relationships between Music-impression, Visual-impression and Music Video Clip’s Impression,” 2018. [Online]. Available: http://www.music-ir.org/mirex/wiki/MIREX.

B. Saini, V. Singh, and S. Kumar, “Information Retrieval Models and Searching Methodologies : Survey,” Int. J. Adv. Found. Res. Sci. Eng., vol. 1, no. 2, pp. 57–62, 2014.

IngwersenPeter and JärvelinKalervo, “Information retrieval in context,” ACM SIGIR Forum, vol. 39, no. 2, pp. 31–39, Dec. 2005, doi: 10.1145/1113343.1113351.

D. Stoller and P. Thesis, “Deep Learning for Music Information Retrieval in Limited Data Scenarios,” 2020.

I. G. Harsemadi, “Perbandingan Distance Measure Pada K-Means Clustering Untuk Pengelompokkan Musik Terhadap Suasana Hati,” Univ. AMIKOM Yogyakarta, 2018, [Online]. Available: www.audionetwork.com.

I Komang Setia Buana, “Aplikasi Untuk Pengoprasian Komputer Dengan Mendeteksi Gerakan Menggunakan Opencv Python,” 2018.

M. Goto, “A chorus section detection method for musical audio signals and its application to a music listening station,” IEEE Trans. Audio, Speech Lang. Process., vol. 14, no. 5, pp. 1783–1794, Sep. 2006, doi: 10.1109/TSA.2005.863204.

P. R. Sihombing and A. M. Arsani, “Perbandingan Metode Machine Learning Dalam Klasifikasi Kemiskinan Di Indonesia Tahun 2018,” J. Tek. Inform. (JUTIF), Vol. 2, No. 1, Juni 2021, hlm. 51-56, vol. 2, no. 1, pp. 51–56, 2021.