• DocumentCode
    569167
  • Title

    An Efficient Query-by-Singing/Humming System Based on Fast Fourier Transforms of Note Sequences

  • Author

    Wei-Ho Tsai ; Yu-Ming Tu

  • Author_Institution
    Dept. of Electron. Eng., Nat. Taipei Univ. of Technol., Taipei, Taiwan
  • fYear
    2012
  • fDate
    9-13 July 2012
  • Firstpage
    521
  • Lastpage
    525
  • Abstract
    This paper presents a query-by-singing/humming method that enables fast melody comparison. The basic idea is to measure the distances between note sequences in the frequency domain instead of time domain. Thanks to the merit of fast Fourier transform, we can convert different-length note sequences into equal-dimension vectors via zero padding. The equal dimensionality allows us to compare the vectors using Euclidean distance directly, which avoids performing time-consuming alignment between sequences. To take both efficiency and effectiveness into account, the proposed fast melody comparison method is combined with dynamic time warping technique into a two-stage sequence matching system. Our experiments conducted using the MIREX 2006 database demonstrate the feasibility of the proposed system.
  • Keywords
    audio signal processing; distance measurement; fast Fourier transforms; frequency-domain analysis; music; pattern matching; query processing; time-domain analysis; Euclidean distance; MIREX 2006 database; distance measurement; dynamic time warping; equal-dimension vector; fast Fourier transform; fast melody comparison; frequency domain; note sequence; query-by-singing/humming system; time domain; two-stage sequence matching system; zero padding; Complexity theory; Databases; Fast Fourier transforms; Frequency measurement; Multimedia communication; Music information retrieval; Vectors; dynamic time warping; fast Fourier transform; query-by-humming; query-by-singing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multimedia and Expo (ICME), 2012 IEEE International Conference on
  • Conference_Location
    Melbourne, VIC
  • ISSN
    1945-7871
  • Print_ISBN
    978-1-4673-1659-0
  • Type

    conf

  • DOI
    10.1109/ICME.2012.80
  • Filename
    6298454