DOI QR코드

DOI QR Code

Algorithm to Search for the Original Song from a Cover Song Using Inflection Points of the Melody Line

멜로디 라인의 변곡점을 활용한 커버곡의 원곡 검색 알고리즘

  • 이보현 (이화여자대학교 컴퓨터공학과) ;
  • 김명 (이화여자대학교 컴퓨터공학과)
  • Received : 2020.12.18
  • Accepted : 2021.02.26
  • Published : 2021.05.31

Abstract

Due to the development of video sharing platforms, the amount of video uploads is exploding. Such videos often include various types of music, among which cover songs are included. In order to protect the copyright of music, an algorithm to find the original song of the cover song is essential. However, it is not easy to find the original song because the cover song is a modification of the composition, speed and overall structure of the original song. So far, there is no known effective algorithm for searching the original song of the cover song. In this paper, we propose an algorithm for searching the original song of the cover song using the inflection points of the melody line. Inflection points represent the characteristic points of change in the melody sequence. The proposed algorithm compares the original song and the cover song using the sequence of inflection points for the representative phrase of the original song. Since the characteristics of the representative phrase are used, even if the cover song is a song made by modifying the overall composition of the song, the algorithm's search performance is excellent. Also, since the proposed algorithm uses only the features of the inflection point sequence, the memory usage is very low. The efficiency of the algorithm was verified through performance evaluation.

동영상 공유 플랫폼의 발전으로 인해 동영상 업로드 분량이 폭발적으로 증가하고 있다. 그러한 동영상에는 다양한 형태의 음악이 포함되는 경우가 많으며, 그중에는 커버곡이 포함된다. 음악의 저작권을 보호하기 위해서는 커버곡의 원곡을 찾아내는 알고리즘이 필요하지만, 커버곡은 원곡의 조성, 속도와 전체적인 구성이 변형된 것이기 때문에 커버곡의 원곡을 찾기는 쉽지 않다. 이와 같이 변형된 커버곡으로부터 원곡을 검색하는 효율적인 알고리즘은 현재까지 알려진 바가 없다. 이에 본 연구에서는 멜로디 라인의 변곡점들을 활용한 커버곡의 원곡 검색 알고리즘을 제안한다. 변곡점은 멜로디 시퀀스에서 특징적인 변화 지점을 나타낸다. 제안하는 알고리즘은 원곡의 대표 구절에 대한 변곡점 시퀀스를 사용하여 원곡과 커버곡을 비교한다. 원곡의 대표 구절의 특징을 사용하기 때문에 커버곡이 전체적인 곡의 구성을 변형하여 만들어진 곡이라고 해도, 알고리즘의 검색 성능이 우수하다. 또한, 제안한 알고리즘은 변곡점 시퀀스의 특징만을 저장하고 사용하므로 메모리 사용량이 매우 적다. 알고리즘의 효율성은 성능평가를 통해 검증하였다.

Keywords

References

  1. J. Seo, "Improving Cover Song Search Accuracy by Extracting Salient Chromagram Components," Journal of Korea Multimedia Society, Vol.22, No.6, pp.639-645, 2019. https://doi.org/10.9717/KMMS.2019.22.6.639
  2. A. Ghias, J. Logan, D. Chamberlin, and B. C. Smith, "Query by humming: musical information retrieval in an audio database," in Proceedings of the third ACM international conference on Multimedia (MULTIMEDIA '95), Association for Computing Machinery, New York, NY, USA, pp.231-236, 1995.
  3. J. Jee and H. Oh, "Design and Implementation of Music Information Retrieval System," The Transactions of the Korea Information Processing Society, Vol.5, No.1, pp.1-11, 1998.
  4. D. P. W. Ellis, and G. E. Poliner, "Identifying 'Cover Songs' with Chroma Features and Dynamic Programming Beat Tracking," 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07, Honolulu, HI, pp.IV-1429-IV-1432, 2007.
  5. "Cultural Technology (CT) In-depth Report: Music information retrieval technology trend," Korea Creative Content Agency, No.4, pp.1-19, 2012.
  6. J. Choi, J. Yoon, G. Kim, J. Ahn, and J. Jung, "Extraction of Music Highlight via Improved Similarity Anaylysis," Proceedings of Korean Institute of Information Scientists and Engineers, pp.1818-1820, 2018.
  7. S. Geum and J. Nam, "Music information retrieval examined by melody extraction algorithm," The Magazine of the IEIE, Vol.43, No.5, pp.41-49, 2016.
  8. J. Salamon and E. Gomez, "Melody Extraction from Polyphonic Music Signals using Pitch Contour Characteristics," IEEE Transactions on Audio, Speech and Language Processing, Vol.20, No.6, pp.1759-1770, 2012.
  9. D. Oh and H. Oh, "A Similarity Computation Algorithm for Music Retrieval System Based on Query By Humming," Journal of The Korea Society of Computer and Information, Vol.11, No.4, pp.137-145, 2006.
  10. W. Heo, B. Jang, H. Jo, J. Kim, and O. Kwon, "Performance of music section detection in broadcast drama contents using independent component analysis and deep neural networks," Journal of the Korean Society of Speech Sciences, Vol.10, No.3, pp.19-29, 2018.
  11. J. Park and S. Kim, "Development of a System for Music Plagiarism Detection Using Melody Databases," Journal of Korea Multimedia Society, Vol.8, No.1, pp.1-8, 2005.
  12. Y. Fan, Y. Shi, K. Kang, and Q. Xing, "An Inflection Point Based Clustering Method for Sequence Data," In Web Information Systems and Applications. WISA 2019. Lecture Notes in Computer Science, Vol.11817. Springer, Cham, 2019.