marytts.machinelearning
Class GMMTrainer

java.lang.Object
  extended by marytts.machinelearning.GMMTrainer

public class GMMTrainer
extends java.lang.Object

Expectation-Maximization (EM) based GMM training Reference: A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from in- complete data via the em algorithm. Journal of the Royal Statistical Society: Series B, 39(1):1–38, November 1977.

Author:
Oytun Türk

Field Summary
 double[] logLikelihoods
           
 
Constructor Summary
GMMTrainer()
           
 
Method Summary
 GMM expectationMaximization(double[][] x, GMM initialGmm, int emMinimumIterations, int emMaximumIterations, boolean isUpdateCovariances, double tinyLogLikelihoodChangePercent, double minimumCovarianceAllowed)
           
static void main(java.lang.String[] args)
           
static void testEndianFileIO()
           
 GMM train(double[][] x, GMMTrainerParams gmmParams)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

logLikelihoods

public double[] logLikelihoods
Constructor Detail

GMMTrainer

public GMMTrainer()
Method Detail

train

public GMM train(double[][] x,
                 GMMTrainerParams gmmParams)

expectationMaximization

public GMM expectationMaximization(double[][] x,
                                   GMM initialGmm,
                                   int emMinimumIterations,
                                   int emMaximumIterations,
                                   boolean isUpdateCovariances,
                                   double tinyLogLikelihoodChangePercent,
                                   double minimumCovarianceAllowed)

testEndianFileIO

public static void testEndianFileIO()
                             throws java.io.IOException
Throws:
java.io.IOException

main

public static void main(java.lang.String[] args)