Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Voiced frames duration #35

Closed
ropok opened this issue Jul 16, 2019 · 1 comment
Closed

Voiced frames duration #35

ropok opened this issue Jul 16, 2019 · 1 comment

Comments

@ropok
Copy link

ropok commented Jul 16, 2019

Hello, how to decide the duration of the voiced frames?
Because for now the result is to short..

I want to make it longer, like 1 second of silence then the voice appear and then 1 second of silence in the ending.

@jonnor
Copy link

jonnor commented May 16, 2020

One approach is to post-process the VAD output. If you want 1 second gaps at the start and end, subtract 1 second from start time, and add one second to the end time. This is called padding.
This might end up with overlapping regions, which you may want to merge into one region.

Another common post-processing is to merge regions which are very close to eachother. For example to merge regions that are less than 1 seconds apart into one region.

@wiseman wiseman closed this as completed May 26, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants