DiscardShortSegs

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.

Type: Decimal
Default: speakerid module: 1.0
audiotemplatescore module: 1.0
ivscore module: 2.0
Required: No
Configuration Section: audiotemplatescore, ivscore, and speakerid modules
Example: DiscardShortSegs=3.0
See Also: DiscardShort (action parameter)
MinNonSpeech
MinSpeech

_FT_HTML5_bannerTitle.htm