Hacker News new | past | comments | ask | show | jobs | submit login

The fact that this is still a difficult problem makes me think we haven’t progressed that far yet with ML and AI.



I don't believe it's a difficult problem - no need for ML/AI since removing vocals was / has been done decades ago already, see karaoke - it's just that nobody's bothered to build it. Plus, adapting a song like that has legal implications; iirc you can't just release a karaoke version of a song for example.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: