Package edu.cmu.sphinx.frontend.feature

Provides classes that processes features.

See:
Description

Class Summary

AbstractFeatureExtractor	Abstract base class for windowed feature extractors like DeltasFeatureExtractor, ConcatFeatureExtractor or S3FeatureExtractor.
BatchAGC	Applies automatic gain control (CMN)
BatchCMN	Applies cepstral mean normalization (CMN), sometimes called channel mean normalization, to incoming cepstral data.
ConcatFeatureExtractor	This component concatenate the cepstrum from the sequence of frames according to the window size.
DeltasFeatureExtractor	Computes the delta and double delta of input cepstrum (or plp or ...).
FrameDropper	Drops certain feature frames, usually to speed up decoding.
LDA	Implements an LDA transformation.
LiveCMN	Subtracts the mean of all the input so far from the Data objects.
S3FeatureExtractor	Computes the delta and double delta of input cepstrum (or plp or ...).

Package edu.cmu.sphinx.frontend.feature Description

Provides classes that processes features. Examples include batch mode cepstral mean normalization, and the computation of delta and double delta of features.