this post was submitted on 01 Apr 2024
24 points (100.0% liked)

Free and Open Source Software

17934 readers
42 users here now

If it's free and open source and it's also software, it can be discussed here. Subcommunity of Technology.


This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

founded 2 years ago
MODERATORS
 

I've recently done some talks for my schools cybersecurity club, and now I want to edit them.

My actual video editing needs are very simple, I just need to clip parts of the video out, which basically every editor can do, as per my understanding.

However, my videos were recorded from my phone, and I don't have a presentation mic or anything of the sort, meaning background noise, including people talking has slipped in. From my understanding, it's trivial to filter out general noise from audio, as human voices have a specific frequency, even "live", like during recording or during a game, but filtering voices is harder.

However, it seems that AI can do this:

https://scribe.rip/axinc-ai/voicefilter-targeted-voice-separation-model-6fe6f85309ea

Although, it seems to only work on .wav audio files, meaning I would need to separate out the audio track first, convert it to wav, and then re merge it back in.

Before I go learning how to do this, I'm wondering if there is already an existing FOSS video editor, or plugin to an editor that lets me filter the video itself, or a similar software that works on the audio of videos.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 1 points 7 months ago

It's possible that there's a reason it requires lossless audio, in that it requires uncompressed signal to work. For instance, if the ML model is trained on uncompressed data, it may need audio which has never been compressed.