HPE 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 DiscardShortSegs
to a minimum segment length.
sidoptimizer
module discards segments with durations below the specified value.speakerid
module returns a result of 'Unknown
' for any section with a duration below the specified value.audiotemplatescore
module returns a result of 'Unknown
' for any section with a duration below the specified value.
Type: | Decimal |
---|---|
Default: |
|
Required: | No |
Configuration Section: | audiotemplatescore, sidoptimizer, and speakerid modules |
Example: | DiscardShortSegs=3.0
|
See Also |
DiscardShort (action parameter) |
|