The maximum size (in seconds) of speech segments.
You might want to restrict the maximum length of a speech segment in speaker identification because HPE IDOL Speech Server must wait for a speech segment to finish before it runs speaker segmentation and identification.
Reducing the maximum speech segment size might improve the latency in speaker identification. However, reducing it by too much might affect the accuracy of the results.
By default, the maximum length of non-speech segments is not limited.
Type: | Decimal |
Default: | 0.0 (unlimited) |
Required: | No |
Configuration Section: | speakerid module |
Example: | MaxSpeech=10.0
|
See Also: | MaxSpeech (action parameter) MaxNonSpeech MinSpeech MinNonSpeech |
|