Open topic with navigation

Run Audio Analysis

As an alternative to using the different individual audio preprocessing options, you can use the audioAnalysis task to combine a number of the key audio preprocessing tasks that are supported by the audiopreproc module in a single task. The audioAnalysis task includes the following functions:

• Audio classification, as provided in the speechSilClassification task. DTMF and dial tones can optionally be included in the output, by using the DoToneClass parameter.
• Overall and segmented signal-to-noise ratio (SNR), as provided in the SNRCalculation task.
• Clipping detection, as provided in the ClippingDetection task.
• Audio quality summary, which is unique to the AudioAnalysis task.

To run audio analysis

• Send an AddTask action to IDOL Speech Server, and set the following parameters:

  File	The audio file to process.
  Out	The XML file to write the audio analysis summary results to.

For example:

http://localhost:15000/action=AddTask&Type=AudioAnalysis&File=C:\data\Sample.wav&Out=SampleAnalysis.xml

This action performs audio analysis on the Sample.wav file and writes the results to the SampleAnalysis.xml file.

The AudioAnalysis task also produces an additional audio classification .ctm file. By default, this file has the same name as the task token. You can use the GetResults action with the label parameter set to class to retrieve this file.

For more information, see the IDOL Speech Server Reference.