Welcome, Guest
Username: Password: Remember me

NOTE: This is a "Community" forum. Please be mindful that community members are here to help as part of a community effort. We therefore appreciate your effort in keeping this forum a happy place!

If you have a specific issue (e.g. hardware, failure) and want help from our support team, please use our tech support portal (Support menu - > Contact Us).
Thanks a lot of your help in making a better community.
  • Page:
  • 1

TOPIC:

Voice activated detection (VAD) parameter settings 2 years 8 months ago #39034

  • YukChow
  • YukChow's Avatar Topic Author
  • Offline
  • New Member
  • New Member
  • Posts: 8
  • Thank you received: 0
Hi,

I am testing a uma-8 v1 for my voice-based chatbot.
The default setting of the VAD parameters on the board booted up are given in below (also see the attachment vad_settings.png)

VAD Detect Time: 25000
VAD Timeout: 2000
VAD Threshold Enter: 2
VAD Threshold Exit: 50

Can anyone provide some guideline on setting these parameters? For my application, only some short utterances are needed.

Also, in the uma-8 user manual indicates that the default value of VAD Detect Time is 2 samples which equivalent to the attack time before VAD is enabled. What is this mean? Please advise, thanks.

Attachments:

Please Log in or Create an account to join the conversation.

  • Page:
  • 1
Moderators: devteam