Nonlinear dimensionality reduction for efficient and effective audio similarity searching


In this paper, we address the issue of nonlinear dimensionality reduction to efficiently index spectral audio similarity measures. We propose the embedding of the spectral similarity space to a low-dimensional Euclidean space. This guarantees the triangular inequality and allows the adoption of several indexing schemes. We enlighten the advantages of the proposed indexable method against recently proposed spectral similarity measures that are also indexable. Moreover, our method compares favorably to linear dimensionality reduction methods, like multidimensional scaling (MDS). The proposed method significantly reduces the computation time during the construction process compared to any audio measure and, simultaneously, minimizes the searching cost for similar songs. To the best of our knowledge, the important issue of audio similarity measures’ scalability is addressed for the first time.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10


  1. 1.

  2. 2.

    We have used the following index implementations: M-tree:, R-tree:, LSH:

  3. 3.

  4. 4.

  5. 5.

  6. 6.


  1. 1.

    Aucouturier J-J (2006) Ten experiments on the modeling of polyphonic timbre. PhD thesis, University of Paris 6, France

  2. 2.

    Aucouturier J-J, Pachet F (2004) Improving timbre similarity: how high is the sky? Journal on Negative Results in Speech and Audio Sciences 1:1–11

    Google Scholar 

  3. 3.

    Baumann S (2005) Music similarity and visualization for music IR. In: Tutorial in 6th international symposium on music information retrieval (ISMIR), London

  4. 4.

    Berenzweig A, Logan B, Ellis D, Whitman B (2003) A large-scale evaluation of acoustic and subjective music similarity measures. Comput Music J 28:63–76

    Article  Google Scholar 

  5. 5.

    Borg I, Groenen P (2005) Modern multidimensional scaling: theory and applications. Springer-Verlag, New York

    MATH  Google Scholar 

  6. 6.

    Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30:1145–1159

    Article  Google Scholar 

  7. 7.

    Chakrabarti K, Keogh E, Mehrotra S, Pazzani M (2002) Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans Database Syst 27:188–228

    Article  Google Scholar 

  8. 8.

    Ciaccia P, Patella M, Zezula P (1997) M-tree: an efficient access method for similarity search in metric spaces. In: Proceedings of 23rd international conference on very large data bases (VLDB). Athens, Greece, pp 426–435

  9. 9.

    de Silva V, Tenenbaum JB (2002) Global versus local methods in nonlinear dimensionality reduction. In: Proceedings of neural information processing systems (NIPS), Vancouver, pp 705–712

  10. 10.

    Gionis A, Indyk P, Motwani R (1999) Similarity search in high dimensions via hashing. In: Proceedings of 25th international conference on very large data bases (VLDB), Edinburgh, pp 518–529

  11. 11.

    Guttman A (1984) R-Trees: a dynamic index structure for spatial searching. In: Proceedings of ACM international conference on management of data (SIGMOD), Boston, pp 47–57

  12. 12.

    Jensen JH, Ellis D, Christensen MG, Jensen SH (2007) Evaluation distance measures between Gaussian mixture models of MFCCs. In: Proceedings of 8th international symposium on music information retrieval (ISMIR), Vienna, pp 107–108

  13. 13.

    Keogh E, Chakrabarti K, Pazzani M, Mehrotra S (2001) Dimensionality reduction for fast similarity search in large time series databases. Knowl Inf Syst 3:263–286

    MATH  Article  Google Scholar 

  14. 14.

    Kouropteva O, Okun O, Pietikäinen M (2005) Incremental locally linear embedding. Pattern Recogn 38:1764–1767

    MATH  Article  Google Scholar 

  15. 15.

    Logan B, Salomon A (2001) A music similarity function based on signal analysis. In: Proceedings of IEEE international conference on multimedia and expo (ICME), Tokyo, pp 745–748

  16. 16.

    Pampalk E, Flexer A, Widmer G (2005) Improvements of audio-based music similarity and genre classification. In: Proceedings of 6th international symposium on music information retrieval (ISMIR), London, pp 628–633

  17. 17.

    Pohle T, Schnitzer D (2007) Striving for an improved audio similarity measure. MIREX 2007-audio music similarity and retrieval (

  18. 18.

    Provost FJ, Fawcett T (1997) Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions. In: Proceedings of international conference on knowledge discovery and data mining (KDD), Newport Beach, pp 43–48

  19. 19.

    Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290:2323–2326

    Article  Google Scholar 

  20. 20.

    Vu K, Hua LA, Cheng H, Lang S (2006) A non-linear dimensionality-reduction technique for fast similarity search in large databases. In: ACM international conference on Management of Data (SIGMOD), Chicago, pp 527–538

Download references

Author information



Corresponding author

Correspondence to Dimitris Rafailidis.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Rafailidis, D., Nanopoulos, A. & Manolopoulos, Y. Nonlinear dimensionality reduction for efficient and effective audio similarity searching. Multimed Tools Appl 51, 881–895 (2011).

Download citation


  • Audio similarity searching
  • Content based retrieval
  • Music database
  • Nonlinear dimensionality reduction