Gender

Prev Next

Evaluates the gender of speaker of the input voice.

Parameters

name
description
default
Address Address of the gender service http://core-audio-gender-age
ConfidenceThreshold A threshold between 0.0 and 1.0. Gender detection results with less confidence than this value will be ignored. 0.8
IgnoreSslErrors ignore any certificate errors if emotion address contains https false

Inputs

Audio

 Accepts audio from a single channel.

Events

 none

Outputs

Audio

 none

Events

name description
Gender Change This event is raised once when the gender of the speaker is detected, it will be raised again each time the gender of the speaker changes.

Remarks

  • This node evaluates the speech in segments of 3 seconds. Silent periods are not included in this duration.

Project Structure

The Gender Node only needs audio input. The audio doesn't have to be segmented. So, you can place the gender node wherever the desired audio is flowing through. A simple project can be built as such:

image.png

However, a better approach would be:

image.png

Why this approach is better:

In the second example, the only difference is that we pass the audio through a VAD node. This means the audio is filtered. The only audio info that passes through a VAD is speech info. This approach will result in better confidence levels in Gender identification since random silences are cleared.

Supported flow types

Stream, Batch

Release Notes

v3.1.0
  • Fixed a rarely observed crash while responding to Stop
v1.0.0
  • Introduced node.