Which is the Better Entropy Expression for Speech Processing: -S Log S or Log S?

Abstract

In maximum-entropy spectral analysis (MESA), one maximizes the integral of log S(f), where S(f) is a power spectrum. The resulting spectral estimate, which is equivalent to that obtained by linear prediction and other methods, is popular in speech-processing applications. An alternative expression, -S(f)log S(f), is used in optical processing and elsewhere. This report considers whether the alternative expression leads to spectral estimates useful in speech processing. The authors investigate the question both theoretically and empirically. The theoretical investigation is based on generalizations of the two estimates-the generalizations take into account prior estimates of the unknown power spectrum. It is shown that both estimates result from applying a generalized version of the principle of maximum entropy, but they differ concerning the quantities that are treated as random variables. The empirical investigation is based on speech synthesized using the different spectral estimates. Although both estimates lead to intelligible speech, speech based on the MESA estimate is qualitatively superior. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 20, 1983
Accession Number
ADA131735

Entities

People

  • John E. Shore
  • Rodney Johnson

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Autocorrelation
  • Computations
  • Data Processing
  • Distortion
  • Estimators
  • Frequency
  • Image Processing
  • Power Spectra
  • Probability
  • Probability Distributions
  • Random Variables
  • Spectra
  • Standards
  • Stationary Processes
  • Stochastic Processes
  • Time Domain

Readers

  • Speech Processing/Speech Recognition.
  • Statistical inference.