Run an Audio Preprocessing Task

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

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:


_FT_HTML5_bannerTitle.htm