The ClusterSpeechTel
task clusters telephony speech into speaker segments. For example, if two speaker clusters are identified, the output labels are Cluster_0
and Cluster_1
respectively.
Parameter | Description | Required |
---|---|---|
Type | The task name. Set to ClusterSpeechTel . |
Yes |
File | The input audio file. | |
FixTime | A fixed size for speaker clusters. | |
MaxNumSpeakers | The final maximum number of speakers to produce. | |
MergeThresh | The threshold below which to merge clusters. | |
MinNumSpeakers | The final minimum number of speakers to produce. | |
NormFile | The acoustic normalization file to use. | |
Out | The file that IDOL Speech Server writes task output to. | |
SampleFrequency | The sample frequency of the audio file to process. | |
SilThresh | The threshold between what the task identifies as silence and non-silence. | |
SpeechThresh | The threshold between speech and non-speech (music or noise). | |
SugdInputChannels | The channel layout of the input media file. | |
SugdInputFrequency | The sampling rate of the input media file. |
http://localhost:13000/action=AddTask&Type=ClusterSpeechTel&File=1h.wav&Lang=ENUK-tel&Out=outTel
This action uses port 15000
to instruct IDOL Speech Server, which is located on the local machine, to cluster the data in the 1h.wav
telephony audio file into speaker segments, and to write the results to the outTel
output file.
|