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. | |
| Lang | The name of a language pack. | Yes |
| 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. | |
| Out | The file that IDOL Speech Server writes task output to. | |
| 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.
|
|