Blind Music Timbre Source Isolation by Multi- resolution Comparison of Spectrum Signatures

  • Xin Zhang
  • Wenxin Jiang
  • Zbigniew W. Ras
  • Rory Lewis
Conference paper

DOI: 10.1007/978-3-642-13529-3_65

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6086)
Cite this paper as:
Zhang X., Jiang W., Ras Z.W., Lewis R. (2010) Blind Music Timbre Source Isolation by Multi- resolution Comparison of Spectrum Signatures. In: Szczuka M., Kryszkiewicz M., Ramanna S., Jensen R., Hu Q. (eds) Rough Sets and Current Trends in Computing. RSCTC 2010. Lecture Notes in Computer Science, vol 6086. Springer, Berlin, Heidelberg

Abstract

Automatic indexing of music instruments for multi-timbre sounds is challenging, especially when partials from different sources are overlapping with each other. Temporal features, which have been successfully applied in monophonic sound timbre identification, failed to isolate music instrument in multi-timbre objects, since the detection of the start and end position of each music segment unit is very difficult. Spectral features of MPEG7 and other popular features provide economic computation but contain limited information about timbre. Being compared to the spectral features, spectrum signature features have less information loss; therefore may identify sound sources in multi-timbre music objects with higher accuracy. However, the high dimensionality of spectrum signature feature set requires intensive computing and causes estimation efficiency problem. To overcome these problems, the authors developed a new multi-resolution system with an iterative spectrum band matching device to provide fast and accurate recognition.

Keywords

Blind Music Sound SourcesIsolation STFT (Short-Time Fourier Transform) Automatic Indexing KNN Spectral Features 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Xin Zhang
    • 1
  • Wenxin Jiang
    • 2
  • Zbigniew W. Ras
    • 2
    • 4
    • 5
  • Rory Lewis
    • 3
  1. 1.Dept. of Math. and Comp. ScienceUniv. of North CarolinaPembrokeUSA
  2. 2.Dept. of Comp. ScienceUniv. of North CarolinaCharlotteUSA
  3. 3.Dept. of Comp. ScienceUniv. of ColoradoColorado SpringsUSA
  4. 4.Polish-Japanese Institute of Information TechnologyWarsawPoland
  5. 5.Institute of Comp. SciencePolish Academy of SciencesWarsawPoland

Personalised recommendations