The SegmentWav
task is deprecated in IDOL Speech Server version 11.5 and later. Use the ClusterSpeech task instead.
This task is still available for existing implementations, but it might be incompatible with new functionality. The task might be deleted in future.
The SegmentWav
task segments an audio file by speaker. The task does not require any speaker identification information because IDOL Speech Server estimates speaker changes from changes in the audio.
Parameter | Description | Required |
---|---|---|
Type | The task name. Set to SegmentWav . |
Yes |
File | The audio file to process. | Yes |
MaxSeg | The maximum duration of an audio segment in seconds. | |
MinSeg | The minimum duration of an audio segment in seconds. | |
NormFile | The acoustic normalization file (.ian file from language pack) to use. | Yes |
Out | The file to write the results to. | Yes |
Sensitivity | Controls the number of segments that are produced. |
http://localhost:15000/action=AddTask&Type=SegmentWav&File=C:\Data\Speech.wav&NormFile=C:\LP\ver-ENUK-5.0-16k.ian&Out=SpeakerChanges.ctm
This action estimates speaker changes in the Speech.wav
file and writes the results to the SpeakerChanges.ctm
file.
|