IDOL Speech Server initially segments audio by speaker and then identifies the speaker in each segment. Short segments can lower identification accuracy and you can choose to exclude short segments from speaker identification by setting DiscardShort to a minimum segment length.
WavSidOptimize and StreamSidOptimize tasks discard segments with durations below the specified value.WavSpeakerId and StreamSpeakerId tasks return a result of 'Unknown' for any section with a duration below the specified value.SpkIdEvalWav and SpkIdEvalStream tasks return a result of 'Unknown' for any section with a duration below the specified value.| Action: | AddTask, CheckResources |
|---|---|
| Task: | SpkIdEvalStream , SpkIdEvalWav , StreamSidOptimize, StreamSpeakerId, WavSidOptimize, WavSpeakerId |
| Type: | Decimal |
| Default: |
|
| Example: | DiscardShort=1.0
|
| See Also: | DiscardShortSegs (configuration parameter) |
|
|