Hacker News Reader

It would be great for practicing songs. In this scenario you would be clicking on the instrument to turn off.

matching faces with voices in a surveillance situation, which person is talking?

That's actually this paper: https://ai.googleblog.com/2018/04/looking-to-listen-audio-vi...

that's actually a whole subfield, not "this paper".

For the sound splitting, it's probably not extremely useful. You can however use this frequency analysis from video to synchronise audio with a video (for a music video where you want to use a studio audio recording with a video clip)