Speech Features Extraction Using Cone-Shaped Kernel Distribution

  • Authors:

  • Janez Zibert;France Mihelic;Nikola Pavesic

  • Affiliations:

  • -;-;-

  • Venue:
  • TSD '02 Proceedings of the 5th International Conference on Text, Speech and Dialogue
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper reviews two basic time-frequency distributions, spectrogram and cone-shaped kernel distribution. We study, analyze and compare properties and performance of these quadratic representations on speech signals. Cone-shaped kernel distribution was successfully applied to speech features extraction due to several useful properties in time-frequency analysis of speech signals.