Advertisement

Cross-Similarity Measurement of Music Sections: A Framework for Large-scale Cover Song Identification

  • Kang CaiEmail author
  • Deshun Yang
  • Xiaoou Chen
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 63)

Abstract

For large-scale cover song identification, most previous works take a single feature vector as the representation of a song. Although this approach ensures structure invariance, it may cause overcorrection since it totally neglects the structure feature of the song. To address this problem, we put forward a novel framework for large-scale cover song identification based on music structure segmentation, aiming at matching the irrelevant sections and ignoring the irrelevant ones. In our implementation, we apply the average and weighted average methods to integrating similarities of section pairs. We evaluate the proposed framework based on three representative previous methods, including 2D Fourier magnitude coefficients, chord profiles, and cognition-inspired descriptors. The experimental results show that the all the three methods in our framework significantly outperform those in their original works.

Keywords

cross-similarity measurement music structure segmentation large-scale cover song identification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    R. Typke, F. Wiering, R. C. Veltkamp et al., “A survey of music information retrieval systems.” in ISMIR, 2005, pp. 153–160.Google Scholar
  2. 2.
    J. Serra, E. Gómez, and P. Herrera, “Audio cover song identification and similarity: background, approaches, evaluation, and beyond,” in Advances in Music Information Retrieval. Springer, 2010, pp. 307–332.Google Scholar
  3. 3.
    J. Serra, E. Gómez, P. Herrera, and X. Serra, “Chroma binary similarity and local alignment applied to cover song identification,” ICASSP, 2008.Google Scholar
  4. 4.
    T. Bertin-Mahieux, D. P. Ellis, B. Whitman, and P. Lamere, “The million song dataset,” in ISMIR. University of Miami, 2011, pp. 591–596.Google Scholar
  5. 5.
    D. P. Ellis and B.-M. Thierry, “Large-scale cover song recognition using the 2d fourier transform magnitude,” in ISMIR, 2012, pp. 241–246.Google Scholar
  6. 6.
    E. J. Humphrey, O. Nieto, and J. P. Bello, “Data driven and discriminative projections for large-scale cover song identification.” in ISMIR, 2013, pp. 149–154.Google Scholar
  7. 7.
    M. Khadkevich and M. Omologo, “Large-scale cover song identification using chord profiles.” in ISMIR, 2013, pp. 233–238.Google Scholar
  8. 8.
    J. van Balen, D. Bountouridis, F. Wiering, R. C. Veltkamp et al., “Cognition-inspired descriptors for scalable cover song retrieval,” in ISMIR, 2014.Google Scholar
  9. 9.
    F. Bimbot, E. Deruty, G. Sargent, and E. Vincent, “Methodology and resources for the structural segmentation of music pieces into autonomous and comparable blocks,” 2011.Google Scholar
  10. 10.
    J. Serra, M. Muller, P. Grosche, and J. L. Arcos, “Unsupervised music structure annotation by time series structure features and segment similarity,” IEEE Transactions on Multimedia, vol. 16, no. 5, pp. 1229–1240, 2014.Google Scholar
  11. 11.
    X. Chuan, “Cover song identification using an enhanced chroma over a binary classifier based similarity measurement framework,” in International Conference on Systems and Informatics (ICSAI). IEEE, 2012, pp. 2170–2176.Google Scholar
  12. 12.
    J. Pauwels, F. Kaiser, and G. Peeters, “Combining harmony-based and novelty-based approaches for structural segmentation.” in ISMIR, 2013, pp. 601–606.Google Scholar
  13. 13.
    J. Foote, “Automatic audio segmentation using a measure of audio novelty,” in ICME, vol. 1. IEEE, 2000, pp. 452–455.Google Scholar
  14. 14.
    M. A. Bartsch and G. H. Wakefield, “Audio thumbnailing of popular music using chroma-based representations,” IEEE Transactions on Multimedia, vol. 7, no. 1, pp. 96–104, 2005.Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Institute of Computer Science & TechnologyPeking UniversityBeijingChina

Personalised recommendations