• DocumentCode
    701470
  • Title

    Speech segmentation using multilevel hybrid filters

  • Author

    Zanuy, Marcos Faundez ; Bayes, Francesc Vallverdu

  • Author_Institution
    Department of Signal Theory and Communications (UPC) c/Gran Capità S/N (Campus Nord, Edifici D5) 08034 BARCELONA (SPAIN)
  • fYear
    1996
  • fDate
    10-13 Sept. 1996
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    A novel approach for speech segmentation is proposed, based on Multilevel Hybrid (mean{}/min{}) Filters (MHF) with the following features: • An accurate transition location. • Good performance in noisy environments (gaussian & impulsive noise). The proposed method is based on spectral changes, with the goal of segmenting the voice into homogeneous acoustic segments. This algorithm is being used for phonetically-segmented speech coder, with successful results.
  • Keywords
    Filtering theory; Maximum likelihood detection; Measurement uncertainty; Noise; Nonlinear filters; Speech;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    European Signal Processing Conference, 1996. EUSIPCO 1996. 8th
  • Conference_Location
    Trieste, Italy
  • Print_ISBN
    978-888-6179-83-6
  • Type

    conf

  • Filename
    7083196