Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

A system for recommending audio devices based on frequency band analysis of vocal component in sound source

음원 내 보컬 주파수 대역 분석에 기반한 음향기기 추천시스템

  • 김정현 (대구대학교 대학원 IT융합공학과) ;
  • 석철민 (대구대학교 대학원 IT융합공학과) ;
  • 김민주 (대구대학교 대학원 IT융합공학과) ;
  • 김수연 (대구대학교 컴퓨터정보공학부)
  • Received : 2022.12.11
  • Accepted : 2022.12.26
  • Published : 2022.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

As the music streaming service and the Hi-Fi market grow, various audio devices are being released. As a result, consumers have a wider range of product choices, but it has become more difficult to find products that match their musical tastes. In this study, we proposed a system that extracts the vocal component from the user's preferred sound source and recommends the most suitable audio device to the user based on this information. To achieve this, first, the original sound source was separated using Python's Spleeter Library, the vocal sound source was extracted, and the result of collecting frequency band data of manufacturers' audio devices was shown in a grid graph. The Matching Gap Index (MGI) was proposed as an indicator for comparing the frequency band of the extracted vocal sound source and the measurement data of the frequency band of the audio devices. Based on the calculated MGI value, the audio device with the highest similarity with the user's preference is recommended. The recommendation results were verified using equalizer data for each genre provided by sound professional companies.

음원 스트리밍 서비스와 Hi-Fi 시장이 성장함에 따라 다양한 음향기기들이 출시되고 있다. 이로 인해 소비자들의 제품 선택에 대한 폭은 넓어졌지만 자신의 음악적 취향과 일치하는 제품을 찾기는 더욱 어려워졌다. 본 연구에서는 사용자가 선호하는 음원으로부터 보컬 성분을 추출하고 이를 토대로 사용자에게 가장 적합한 음향기기를 추천하는 시스템을 제안하였다. 이를 위해 먼저 원본 음원을 Python의 Spleeter Library를 통해 분리하여 보컬 음원을 추출하고 제조사의 음향기기의 주파수 대역 데이터를 수집한 결과를 각각 격자 그래프로 나타내었다. 추출한 보컬 음원의 주파수 대역과 음향기기의 주파수 대역 측정치 데이터를 비교하기 위한 지표로서 Matching Gap Index(MGI)를 제안하였다. 산출된 MGI 값을 토대로 사용자 선호와의 유사도가 가장 높은 음향기기를 추천한다. 추천 결과는 음향 전문업체에서 제공하는 장르별 Equalizer 데이터를 이용하여 검증하였다.

Keywords

Acknowledgement

이 논문은 2021학년도 대구대학교 학문후속세대 연구과제로 수행되었음.

References

  1. Choi, Hong-gu and Hwang, Eenjun (2012). Emotion-based Music Recommendation System based on Twitter Document Analysis. KIISE Transactions on Computing Practices, 18(11), 762-76.
  2. Chung, Ji Yun and Kim, Myoung-Jun (2018). A Study on Personalized Music Recommendation Model through Analysis on Users' Music Preference Factors. Journal of Digital Contents Society, 19(11), 2041-2047. https://doi.org/10.9728/dcs.2018.19.11.2041
  3. Hennequin, Romain, Anis Khlif, Felix Voituret and Manue Moussallam (2020) Spleeter: a fast and efficient music source separation tool with pre-trained models. Journal of Open Source Software, 5(50), 2154, https://doi.org/10.21105/joss.02154
  4. Hong, Taeho, Hong, Junwoo, Kim, Eunmi and Kim, Minsu (2022). An Intelligent Recommendation System by Integrating the Attributes of Product and Customer in the Movie Reviews. Journal of Intelligence and Information Systems, 28(2), 1-18. https://doi.org/10.13088/JIIS.2022.28.2.001
  5. Hwang, Se-Won, Kim, Da-yeong, Kim, Eun-Bae, Lee, Ye-Eun, Eom, Ye-Sol and Lee, Ju-Young (2022). Recommender System for the Hobby-Activity-Item Rental Platform using User-based Collaborative Filtering. Journal of Digital Contents Society, 23(6), 985-993. https://doi.org/10.9728/dcs.2022.23.6.985
  6. Jeon, ByeoungKug and Ahn, Hyunchul (2015). A Collaborative Filtering System Combined with Users' Review Mining: Application to the Recommendation of Smartphone Apps. Journal of Intelligence and Information Systems, 21(2), 1-18. https://doi.org/10.13088/JIIS.2015.21.2.01
  7. Kim, Dong Joo and Lim, Kwon Mook (2015). A Music Recommendation Method Using Emotional States by Contextual Information. Journal of The Korea Society of Computer and Information, 20(10), 69-76. https://doi.org/10.9708/JKSCI.2015.20.10.069
  8. Kim, Hyon Hee, Kim, Dong-Geon and Cho, Jin Nam (2013). A Hybrid Music Recommendation System Combining Listening Habits and Tag Information. Journal of The Korea Society of Computer and Information, 18(2), 107-116. https://doi.org/10.9708/JKSCI.2013.18.2.107
  9. Kim, Kyung-Rog, Byeon, Jaehee and Moon, Nammee (2011). Collaborative Filtering Design Using Genre Similarity and Preffered Genre. Journal of The Korea Society of Computer and Information, 16(4), 159-168. https://doi.org/10.9708/jksci.2011.16.4.159
  10. Lee, Hyun Sup, Kim, Minyoung, Lee, Ji-Hoon and Kim, Jin Deog (2020). Implementation of User Recommendation System based on Video Contents Story Analysis and Viewing Pattern Analysis. Journal of the Korea Institute Of Information and Communication Engineering, 24(12), 1567-1573. https://doi.org/10.6109/JKIICE.2020.24.12.1567
  11. Lee, Sang Hoon and Kim, Su-Yeon (2013). Design and Implementation of an Intelligent System for Personalized Contents Recommendation on Smart TVs. Journal of the Korea Society Industrial Information System, 18(4), 73-79.
  12. Lee, Soojung (2020). Collaborative Filtering based Recommender System using Restricted Boltzmann Machines. Journal of The Korea Society of Computer and Information, 25(9), 101-108. https://doi.org/10.9708/JKSCI.2020.25.09.101
  13. McFee, Brian, Alexandros Metsai, Matt McVicar, Stefan Balke, Carl Thome, Colin Raffel, Frank Zalkow, Ayoub Malek, Dana, Kyungyun Lee, Oriol Nieto, Dan Ellis, Jack Mason, Eric Battenberg, Scott Seyfarth, Ryuichi Yamamoto, viktorandreevichmorozov, Keunwoo Choi, Josh Moore, Rachel Bittner, Shunsuke Hidaka, Ziyao Wei, nullmightybofo, Adam Weiss, Dario Herenu, Fabian-Robert Stoter, Lorenz Nickel, Pius Friesch, Matt Vollrath and Taewoon Kim (2022). librosa/librosa: 0.9.1 (0.9.1). Zenodo. https://doi.org/10.5281/zenodo.6097378
  14. Oh, Jae-Taek and Lee, Sang Yong (2019). A Music Recommendation System based on Context-awareness using Association Rules. Journal of Digital Convergence, 17(9), 375-381. https://doi.org/10.14400/JDC.2019.17.9.375
  15. Park, Se-Eun, Yoon, Jae-Hee, Choi, Se-Young, Ha, Su-Gyoung and Lee, Kyoung-Mi (2020). User-friendly Korean conversation learning application using face swap and personalized recommendation. Journal of Digital Contents Society, 21(12), 2125-2133. https://doi.org/10.9728/dcs.2020.21.12.2125
  16. Park, So Yeon, Kim, Ji Yeon, Kang, Youngok, Cho, Nahye and Yoon, Ji Young (2020). Travel Sites Recommendation Considering User's Preferences Shown in User's SNS Photos. Journal of Korean Society for Geospatial Information Science, 28(4), 127-136. https://doi.org/10.7319/kogsis.2020.28.4.127
  17. Sharma, L. and Gera, A. (2013). A Survey of Recommendation System: Research Challenges. International Journal of Engineering Trends and Technology, 55(5), 1989-1992.
  18. Wu, Y. H. and Chen, A. L. (2000). Index structures of user profiles for efficient web page filtering services. In 2012 IEEE 32nd International Conference on Distributed Computing Systems, 644-644.
  19. Yoo, SoYeop and Jeong, OkRan (2015). The YouTube Video Recommendation Algorithm using Users' Social Category. Journal of KIISE, 42(5), 664-670.
  20. Yun, So-Young and Youn, Sung Dae (2020). Item-Based Collaborative Filtering Recommendation Technique Using Product Review Sentiment Analysis. Journal of the Korea Institute Of Information and Communication Engineering, 24(8), 970-977 https://doi.org/10.6109/JKIICE.2020.24.8.970