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: |
AppDnnBase (configuration parameter) |
|