Difference between revisions of "Voice Activity Detection (VAD)"
Jump to navigation
Jump to search
| Line 1: | Line 1: | ||
| + | This article explains the principle of how the Voice Activity Detection (VAD) works.<br> | ||
| + | |||
'''Voice Activity Detection''' (VAD) or '''Sound Detection''' is a feature available for analog audio inputs. <br> | '''Voice Activity Detection''' (VAD) or '''Sound Detection''' is a feature available for analog audio inputs. <br> | ||
Voice Activity Detection samples the peak amplitude detected at the analog audio input every 30 ms and converts it to dB. <br> | Voice Activity Detection samples the peak amplitude detected at the analog audio input every 30 ms and converts it to dB. <br> | ||
| Line 4: | Line 6: | ||
== Configuration == | == Configuration == | ||
| − | + | The Voice Activity Detection configuration is done from [[EMT overview | EMT]]. | |
== Availability == | == Availability == | ||
Revision as of 15:33, 19 September 2017
This article explains the principle of how the Voice Activity Detection (VAD) works.
Voice Activity Detection (VAD) or Sound Detection is a feature available for analog audio inputs.
Voice Activity Detection samples the peak amplitude detected at the analog audio input every 30 ms and converts it to dB.
If the sampled amplitude is continuously above a trigger amplitude for a set duration, then the programmed On Action is triggered.
Configuration
The Voice Activity Detection configuration is done from EMT.
Availability
This function is available from Exigo 1.3.3 and newer.
