Frequency Normalization

  • Alejandro Acero
Chapter
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 201)

Abstract

In this chapter we will discuss the mel-scale cepstral parameters used in Sphinx and some optimizations that we performed on them. Also, an algorithm for frequency normalization based on variable warping of the frequency axis is presented within the framework of minimal VQ distortion. These techniques together decrease the error rate by 15 to 20%.

Keywords

Frequency Axis Female Speaker Human Auditory System Cepstrum Coefficient Warping Parameter 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 1993

Authors and Affiliations

  • Alejandro Acero
    • 1
  1. 1.Carnegie Mellon UniversityUSA

Personalised recommendations