Extracting Audio From a Mix by Singing It – Source Separation via Input Matching

Paris Smaragdis is an assistant professor at the University of Illinois who specializes in research that involves machine listening. This includes source localization (where the sound is coming from), sound recognition (such as a traffic accident at an intersection) and source separation (taking individual voices or instruments out of a mix). Source separation is a difficult problem (here’s a simple but somewhat crude approach you can try), but the approach shown in the demo below is to have the user mimic the audio they want to extract, such as the vocals or a guitar solo. This audio is then extracted from the mix.

Check out the Audio Interface Demo Video here.

Plenty more cool demos of some of the topics listed above can be found here.

Share this post
  , , , , , ,


Leave a Reply

Your email address will not be published. Required fields are marked *