Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Highlight based Lyrics Search Considering the Characteristics of Query

사용자 질의어 특징을 반영한 하이라이트 기반 노래 가사 검색

  • Received : 2016.07.05
  • Accepted : 2016.08.05
  • Published : 2016.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a lyric search method to consider the characteristics of the user query. According to the fact that queries for the lyric search are derived from highlight parts of the music, this paper uses the hierarchical agglomerative clustering to find the highlight and proposes a Gaussian weighting to consider the neighbor of the highlight as well as highlight. By setting the mean of a Gaussian weighting at the highlight, this weighting function has higher weights near the highlight and the lower weights far from the highlight. Then, this paper constructs a index of lyrics with the gaussian weighting. According to the experimental results on a data set obtained from 5 real users, the proposed method is proved to be effective.

본 논문에서는 사용자들이 노래 가사를 입력으로 음악을 검색할 때 사용자의 질의어 특징을 반영한 검색 방법을 제안한다. 일반적으로 노래 가사 검색에서 사용자들이 작성하는 질의어들은 음악 하이라이트 부분에 해당된다는 점을 고려하여 본 논문에서는 노래 가사를 색인할 때, 하이라이트 부분이 더 중요하도록 만든다. 이를 위해 본 논문에서는 응집 계층 군집화를 사용하여 자동으로 음악 하이라이트 부분을 찾고, 하이라이트 부분과 그 주변 부분을 중요하게 고려할 수 있는 가우시안 중요도를 제안한다. 이 가우시안 함수는 평균을 하이라이트 부분으로 설정함으로써 하이라이트에서 가장 높은 값을 가지며, 주변부는 하이라이트보다 낮은 중요도를 가진다. 이렇게 얻어진 중요도와 함께 노래 가사를 색인함으로써 사용자들이 작성한 질의어에 대해 더 부합하는 검색 결과를 제공해준다. 실험에서 실사용자 5명에 대해 다양한 질의 타입들과 함께 평가하였으며, 가중치를 고려하지 않는 비교 모델보다 제안한 방법이 효과적임을 보인다.

Keywords

References

  1. Arnold Schoenberg, Gerald Strang, and Leonard Stein, Fundamentals of musical composition, Faber & Faber, 1999.
  2. Rodger J. McNab, Lloyd A. Smith, Ian H. Witten, Clare L. Henderson, and Sally JoSu Cunningham, "Towards the Digital Music Library: Tune Retrieval from Acoustic Input," In Proceedings of the First ACM International Conference on Digital Libraries, pp. 11-18, 1996.
  3. J. Stephen Downie, "Music information retrieval," Annual Review of Information Science and Technology, Vol. 37. No. 1, pp. 295-340, 2003.
  4. Asif Ghias, Jonathan Logan, David Chamberlin, and Brian C. Smith, "Query by humming: musical information retrieval in an audio database," In Proceedings of the third ACM international conference on Multimedia, pp. 231-236, 1995.
  5. Wei-Ho Tsai, Yu Hung-Ming, and Hsin-Min Wang. "Query-By-Example Technique for Retrieving Cover Versions of Popular Songs with Similar Melodies," In Proceedings of 6th International Society for Music Information Retrieval Conference. pp. 183-190, 2005.
  6. Avery Wang, "The Shazam music recognition service," Communications of the ACM, Vol. 49. No. 8, pp. 44-48, 2006. https://doi.org/10.1145/1125944.1125973
  7. Zhiyuan Guo, Qiang Wang, Gang Liu, and Jun Guo, "A Music Retrieval System Based On Spoken Lyric Queries," International Journal of Advancements in Computing Technology, Vol. 4. No. 8, pp. 173-180. 2012. https://doi.org/10.4156/ijact.vol4.issue8.21
  8. Geun-Tak Chang and Jung-Yun Seo, "Music Recommender System based on Lyrics Information," In Proceedings of the 22th Annual Conference on Human & Cognitive Language Technology, pp. 42-45, 2010.
  9. Tao Wang, Dong-Ju Kim, and Kwang-Seok Hong, "Music Information Retrieval System through Integration of Lyrics and Melody Information," In Proceedings of the Spring Conference of Korean Society for Internet Information, pp. 437-442, 2009.
  10. David Blei, Andrew Y. Ng, and Michael I. Jordan, "Latent Dirichlet Allocation," Journal of Machine Learning Research, Vol. 3, pp. 993-1022, 2003.
  11. Shoto Sasaki, Kazuyoshi Yoshii, Tomoyasu Nakano, Masataka Goto, and Shigeo Morishima, "LYRICRSRADER: A Lyrics Retrieval System Based on Latent Topics of Lyrics," In Proceedings of the 15th International Society for Music Information Retrieval Conference, pp. 585-590, 2014.
  12. Jung-Soon Ro, "A Comparative Analysis of Content-based Music Retrieval Systems," Journal of the Korean Society for Information Management, Vol. 30, No. 3, pp. 23-48, 2013. https://doi.org/10.3743/KOSIM.2013.30.3.023
  13. Peter Knees and Markus Schedl, Music Similarity and Retrieval: An Introduction to Audio- and Web-based Strategies, Springer-Verlag Berlin Heidelberg, 2016.
  14. Nicholas Ring and Alexandra L. Uitdenbogerd, "Finding 'Lucy in disguise': The misheard lyric matching problem," In Proceedings of the 5th Asia Information Retrieval Symposium, pp. 157-167, 2009.
  15. Xin Xu and Tseneo Kato, "Robust and Fast Two-Pass Search Method for Lyric Search Covering Erroneous Queries Due to Mishearing," In Proceedings of CICLing, pp. 306-317, 2012.
  16. Baoxiang Li, Fengxiang Chang, Qiang Wang, Gang Liu, and Jun Guo, "Robust Lyric Search based on Weighted Syllable Confusion Matrix," In Proceedings of the 21st International Conference on Pattern Recognition, pp. 613-616, 2012.
  17. Hussein Hirjee and Daniel G. Brown, "Solving misheard lyric search queries using a probabilistic model of speech sounds," In Proceedings of the 11th International Society for Music Information Retrieval Conference, pp. 147-152, 2010.
  18. Hyungjong Noh, Jeong-Won Cha, and Gary Geunbae Lee, "A Joint Statistical Model for Word Spacing and Spelling Error Correction Simultaneously," In Proceedings of the ACL 2007 Demo and Poster Sessions, pp. 61-64, 2007.
  19. Su Jeong Choi, Hyun-Je Song, Seong-Bae Park, and Sang-Jo Lee, "A POI Categorization by Composition of Onomastic and Contextual Information," In Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence, pp. 38-45, 2014.
  20. E. M. Voorhees, "TREC-8 Question Answering Track Report," In Proceedings of the 8th Text Retrieval Conference, pp. 77-82, 1999.