AppDnnBase

The location of the appResources directory, which contains the DNN and .ian files to use for audio frame categorization. HPE IDOL Speech Server supplies two pairs of files, one for 8 KHz audio, and one for 16 KHz audio.

If you are running HPE IDOL Speech Server in a directory where the appResources directory is copied from the standard installation, you should always set AppDnnBase to appResources/app.

Note: From the 11.2 release, audio preprocessing in HPE IDOL Speech Server uses new DNN technology, which provides improved performance and requires less tailoring of thresholds to specific audio types. The module uses the AppDnnBase parameter and the presence of the nf input to the audiopreproc module to determine whether to use the new DNN technology. If you do not set AppDnnBase, or if the nf input is missing, HPE IDOL Speech Server uses the previous implementation of the audio preprocessing algorithm.

Action: AddTask
Task:

AudioAnalysis, ClusterSpeech, ClusterSpeechTel, ClusterSpeechToTextTel, LangIdFeature, LangIdSegWav, LangIdCumWav, LangIdBndWav, LangIdSegStream, LangIdCumStream, LangIdBndStream, SpeechSilClassification, StreamToTextMusicFilter, StreamToTextMusicFilterPunct

Type: String
Default: appResources/app
Example: AppDnnBase=appResources/app
See also:

AppFrameDupl

FrameDupl

AppDnnBase (configuration parameter)


_HP_HTML5_bannerTitle.htm