edu.cmu.sphinx.frontend.feature
Class ConcatFeatureExtractor

java.lang.Object
  edu.cmu.sphinx.util.props.ConfigurableAdapter
      edu.cmu.sphinx.frontend.BaseDataProcessor
          edu.cmu.sphinx.frontend.feature.AbstractFeatureExtractor
              edu.cmu.sphinx.frontend.feature.ConcatFeatureExtractor

All Implemented Interfaces:

DataProcessor, Configurable

public class ConcatFeatureExtractor
extends AbstractFeatureExtractor

This component concatenate the cepstrum from the sequence of frames according to the window size. It's not supposed to give high accuracy alone, but combined with LDA transform it can give the same or even better results than conventional delta and delta-delta coefficients. The idea is that delta-delta computation is also a matrix multiplication thus using automatically generated with LDA/MLLT matrix we can gain better results. The model for this feature extractor should be trained with SphinxTrain with 1s_c feature type and with cepwin option enabled. Don't forget to set the window size accordingly.

Field Summary

Fields inherited from class edu.cmu.sphinx.frontend.feature.AbstractFeatureExtractor

PROP_FEATURE_WINDOW

Constructor Summary

ConcatFeatureExtractor()

ConcatFeatureExtractor(int window)

Method Summary

Methods inherited from class edu.cmu.sphinx.frontend.feature.AbstractFeatureExtractor

getData, initialize, newProperties

Methods inherited from class edu.cmu.sphinx.frontend.BaseDataProcessor

getPredecessor, getTimer, setPredecessor

Methods inherited from class edu.cmu.sphinx.util.props.ConfigurableAdapter

getName, toString

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

ConcatFeatureExtractor

public ConcatFeatureExtractor(int window)

Parameters:

window -

ConcatFeatureExtractor

public ConcatFeatureExtractor()