Anyone know open source models or papers for splitting audio (that contains human speech and other sounds) into two separate audio files, one containing human speech only and one containing other sounds?

https://speechbrain.github.io/

https://arxiv.org/abs/1611.06265

technical founder/builder of a seed stage AI B2B startup @ycombinator. FID #573

this seems the best among I've tried so far 🙏

Demucs v4 from facebook research was the open source state of the art at this (last I checked).

🇧🇷🇺🇸-  Book: Making Things Think: https://holloway.com/mtt. Investor in Wander, Carry, Footprint, Merkle Manufactory (Farcaster), Dynamic, Paragraph.

Interesting, it seems doable and dataset is relatively easy to synthesize.

I’ve tried to find a good tool for this to help with speech synthesis to get the human speech track but didn’t find anything that worked well

⌐◨-◨ ‘ing around. 
Nouns Fest founder.
Sundae Songs, music publishing, founder.

www.fishandfriends.fun

Never heard of it! Im looking for something that works well with regular speech vs vocals + music

Have you tried Audio Shake?

https://www.audioshake.ai

I’ve been using Spleeter in my workflow for my own music!

Not sure about other audio source separation models

I’ve been using Spleeter in my workflow for my own music!

Not sure about other audio source separation models

https://github.com/deezer/spleeter