You can preprocess audio as a standalone task or as the initial step in other processing tasks. There are four stand-alone preprocessing tasks available out of the box, corresponding to the four audiopreproc
modes.
SpeechSilClassification
|
Classifies segments of audio as speech, non-speech, or music. |
ClippingDetection
|
Detects and assesses clipping in an audio file. |
SNRCalculation
|
Estimates the SNR levels across an audio file. |
DialToneIdentification
|
Detects and identifies dial tones. |
To run a stand-alone audio preprocessing task
Send an AddTask
action to IDOL Speech Server, and set the following parameters:
Type
|
The task name. |
File
|
The audio file to process. To restrict processing to a section of the audio file, set the |
Out
|
The file to write the results to. |
For example:
http://localhost:15000/action=AddTask&Type=SpeechSilClassification&File=C:\Data\Conference.wav&Out=ConfClassification.ctm
This action performs the SpeechSilClassification
task on the Conference.wav
file and writes the results to the ConfClassification.ctm
file.
This action returns a token. You can use the token to:
|