Name a Module Instance

The general syntax for naming a module instance is similar to the syntax for naming stream instances. For each module instance, the syntax is:

ModuleTypeX

where:

ModuleType is the module name.
X is the instance number. The instance number cannot begin with the digit 0. The number is optional–an instance without an assigned number is still treated as unique and different from other instances that have numbers.

For example, stt1 represents the first instance of the stt (speech-to-text) module. wout4 is the fourth instance of the wout module, which is used for handling word labels.

This table contains a complete list of available processing modules.

Module Description
afp Audio fingerprint identification module
afpedit Audio fingerprint database administration module
afpfeature Audio fingerprint feature extraction module
afpfile Audio fingerprint feature file module
afpout Audio fingerprint identification output module
align Transcription alignment module
amadaptadddata

Acoustic model adaptation (data generation) module

DEPRECATED:

The amadaptadddata module is deprecated in IDOL Speech Server version 11.5 and later. HPE recommends that you use the newer Deep Neural Network (DNN) techniques, rather than GMM-based acoustic models.

This module is still available for existing implementations, but it might be incompatible with new functionality. The module might be deleted in future.

amadaptend

Acoustic model adaptation module

DEPRECATED:

The amadaptend module is deprecated in IDOL Speech Server version 11.5 and later. HPE recommends that you use the newer Deep Neural Network (DNN) techniques, rather than GMM-based acoustic models.

This module is still available for existing implementations, but it might be incompatible with new functionality. The module might be deleted in future.

audio Audio file or stream input module
audiopreproc Audio preprocessing module
audiosec Audio security module
audiotemplatedevel Audio template development score module
audiotemplateedit

Speaker set file module

audiotemplatescore Audio template identification module
audiotemplatetrain Speaker template training module
ctm Word input module
filter Stream filter module
fmdcombiner Audio phrase search data file combiner module
frontend Speech feature extraction module
langid Language identification module
lbout

Language identification boundary output module

DEPRECATED:

The lbout module is deprecated in IDOL Speech Server version 11.5 and later. Boundary mode language identification provides the language boundary information in the main output file.

This module is still available for existing implementations, but it might be incompatible with new functionality. The module might be deleted in future.

lfout Language identification feature output module
lidfeature Language identification feature extraction module
lidoptimizer Language identification classifier optimization module
lidout Language identification output module
lidtrain Language identification language training module
lmbuild Custom language model build module
lmtool Language model query module
mixer Combines words from multiple channels into a single timeline
normalizer Audio normalization module
phrasematch Audio phrase match search module
phraseprematch Audio phrase match preprocessing module
plh Audio feature file processing module
postproc Postprocessing module
segment Speaker identification segmentation module
sidout Speaker identification output module
speakerid Speaker identification module
stream

Audio stream input module

DEPRECATED:

The stream module is deprecated in IDOL Speech Server version 11.5 and later. HPE recommends that you use the audio module instead.

This module is still available for existing implementations, but it might be incompatible with new functionality. The module might be deleted in future.

stt Speech-to-text module
textnorm Text normalization module
transcheck Transcription checker module
wav

Audio file input module

DEPRECATED:

The wav module is deprecated in IDOL Speech Server version 11.5 and later. HPE recommends that you use the audio module instead.

This module is still available for existing implementations, but it might be incompatible with new functionality. The module might be deleted in future.

wout Word output module

_HP_HTML5_bannerTitle.htm