[mythtv] A thought on Commercial Flagging -- Long (And rambling)

[Kim Wall]

Jay Jarvinen wrote:

> Perhaps http://aubio.piem.org/ or something similar, could be used to
> map out a rough words-per-minute count.
> 
> Pitch detection is another idea, odds are that the voices/sounds in
> commercials are dissimilar to the program being recorded. Perhaps
> pitch-variation is a better term for what I'm suggesting.

There's also subtile/CC data, which I'd have thought would be a fair bit 
more machine-readable, and could perhaps be bayesian filtered in much 
the same way as email.

3-minute gaps in subs (or a sudden brief appearance of subs in an 
unsubtitled programme) would be a really easy cue for the commercial 
flagger to use.


kim.