search

sergree / matchering

🎚️ Open Source Audio Matching and Mastering
https://pypi.org/project/matchering/
GNU General Public License v3.0
1.8k stars 185 forks source link

Another online mastering service #3

Closed idoleat closed 4 years ago

idoleat commented 5 years ago

It's called eMaster.

Just want to have some discussion. Recently I got plenty of their advertisement on Facebook. I tried to post the link to this repo under the advertised post multiple times, but it got deleted by them every time. They feature themselves as a tool designed by Grammy-winning engineers. Seems like they are trying to convince people online mastering is a thing.

This tool has been put in public for a while. Maybe the market trend is different from before. What's your thoughts on this? I tried to spread this tool to people but I failed🤣 I hope I have time to convert this to NumPy

sergree commented 5 years ago

Nice to meet you, @idoleat!

I can't say anything bad or good about eMastered. Such services like eMastered or LANDR don't give the possibility to upload own reference tracks. They are different. I think it is not good for some music genres like EDM. I talked about it here.

Our code is works like this plugin. But it tries to automate such process as much as possible (compares only loudest parts of both tracks, mid/side separately, etc.).

Seems like they are trying to convince people online mastering is a thing. What's your thoughts on this?

I think everything is possible in the deep learning era. It is the matter of time: Example #1 (not related to mastering); Example #2 (not related to audio).

No, Matchering doesn't use any deep learning / machine learning stuff, just plain DSP with ugly procedural code. But it works well for me and my colleagues who make psy-trance. And for the 10k tracks that were processed on our service, while it was online. It solves this problem: I want my mix to sound like Astrix (insert any artist name) 🤣 (in the context of loudness, spectrum, and width).

I'm afraid to imagine what would happen, if Matchering got a pinch of neural networks. 🎉

idoleat commented 5 years ago

Cool. Matchering with neural networks will be interested. 😃

By the way, actually you can upload reference track to eMastered. You can switch between Normal mastering(without reference) and reference mastering.

sergree commented 5 years ago

You can switch between Normal mastering(without reference) and reference mastering.

Ah, cool. It had no reference mastering in 2017.