For each of the audio files in the adaptation data set, you must produce an audio feature (.plh) file.
To create an audio feature file from an audio file
Send an AddTask
action to HPE IDOL Speech Server, and set the following parameters:
Type
|
The task name. Set to WavToPlh . |
File
|
The audio file to process. |
NormFile
|
The acoustic normalization file (.ian file in the language pack) to use. |
Out
|
The name of the audio feature file to create. |
If the audio file has a frequency of 8 kHz (8,000 Hz), you must also set the following parameter:
Sfreq
|
The sample frequency of the audio file to process–either 8000 or 16000 . If you do not set a value for the Sfreq parameter, HPE IDOL Speech Server uses the default of 16000 . |
For example:
http://localhost:13000/action=AddTask&Type=WavToPlh&File=C:\myData\Speech.wav&NormFile=C:\SPKID\SPKID16k.ian&Out=Speech1.plh
This action uses port 13000
to instruct HPE IDOL Speech Server, which is located on the local machine, to produce the Speech1.plh
feature file from the Speech.wav
audio file, using the SPKID16.ian
normalization file.
This action returns a token. You can use the token to:
The generated audio feature files are used by the adaptation processes described in Present Adaptation Data to HPE IDOL Speech Server.
|