• DocumentCode
    411508
  • Title

    Singing voice features by time-frequency representations

  • Author

    Mesaros, Annamaria ; Lupu, Eugen ; Rusu, Calin

  • Author_Institution
    Fac. of Electron. & Telecommun., Tech. Univ. of Cluj-Napoca, Romania
  • Volume
    1
  • fYear
    2003
  • fDate
    18-20 Sept. 2003
  • Firstpage
    471
  • Abstract
    The goal of this paper is to present an overview of problems related to features of musical signals based on time-frequency distributions. We recall some aspects concerning extraction of the information from time-frequency representations as Friedman distribution and by using orthogonality and singular value decomposition. For robust identification system (singing voice) a more complete characterization of the analyzed signal is needed. Experimental results are also provided.
  • Keywords
    signal representation; singular value decomposition; speech processing; time-frequency analysis; Friedman distribution; musical signals; robust identification system; singing voice features; singular value decomposition; time-frequency representations; Humans; Instruments; Psychology; Robustness; Signal analysis; Signal processing; Singular value decomposition; Speech analysis; Telecommunications; Time frequency analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the 3rd International Symposium on
  • Print_ISBN
    953-184-061-X
  • Type

    conf

  • DOI
    10.1109/ISPA.2003.1296943
  • Filename
    1296943