Package edu.cmu.sphinx.frontend.endpoint

Provides classes and interfaces used for speech endpointing.

See:
Description

Class Summary

ExcessiveNonSpeechPruner	Removes excessive non-speech-segments from a speech stream.
NonSpeechDataFilter	Given a sequence of Data, filters out the non-speech regions.
SpeechClassifiedData	A container for DoubleData class that indicates whether the contained DoubleData is speech or not.
SpeechClassifier	Implements a level tracking endpointer invented by Bent Schmidt Nielsen.
SpeechEndSignal	A signal that indicates the end of speech.
SpeechMarker	Converts a stream of SpeechClassifiedData objects, marked as speech and non-speech, and mark out the regions that are considered speech.
SpeechStartSignal	A signal that indicates the start of speech.

Package edu.cmu.sphinx.frontend.endpoint Description

Provides classes and interfaces used for speech endpointing.

The Sphinx-4 audio endpointer is composed of three data processors that carry out different functions:

SpeechClassifier - classifies chunks of audio into speech and non-speech.

SpeechMarker - marks the audio stream into speech and non-speech regions, by inserting SpeechStartSignals and SpeechEndSignals into the data stream, while giving some 'cushion areas' around these regions.

NonSpeechDataFilter - removes the non-speech regions from the audio.