News for hackers. Stuff that matters.

A comment on Show HN: Shazam-like acoustic fingerprinting of continuous audio streams. Parent comment

Re:Show HN: Shazam-like acoustic fingerprinting of continuou... by fredley on Thursday November 30, 2017 @05:16AM (#15814699)
Sounds like that's potentially solvable by breaking the podcast down into chunks by speaking voice, then flagging any sections of ~30s with a different speaking voice from the rest. Detecting guest speakers shouldn't get caught by this as there'd be more conversation rather than a mostly unbroken 30s chunk.
[ Parent | on HN ]
Re:Show HN: Shazam-like acoustic fingerprinting of continuou... by justinjlynn on Thursday November 30, 2017 @07:07AM (#15815102)
Speaker recognition would be really awesome. Do you know of any techniques more general than fingerprinting specific audio sections?

Edit: https://github.com/ppwwyyxx/speaker-recognition/ looks like the first of a number of good starting points.

[ Parent | on HN ]
Re:Show HN: Shazam-like acoustic fingerprinting of continuou... by dest on Thursday November 30, 2017 @07:49AM (#15815309)
I will publish more on that topic
[ Parent | on HN ]
Re:Show HN: Shazam-like acoustic fingerprinting of continuou... by justinjlynn on Thursday November 30, 2017 @07:04PM (#15820816)
sounds great! looking forward to it.
[ Parent | on HN ]