I have been having problems reliably distinguishing an audio file
containing human voice and on containing sound of data. Most of my
attempts have been with looking for values produced by "sox stats" and
"sox stat". For example, keying off Crest factor misses in some cases.
As files are produced from a gnuradio based application that I can
modify source code of so I would be interested in ways to do this with
gnuradio as well. Any input would be appreciated.
Thanks,
John
_______________________________________________
Discuss-gnuradio mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/discuss-gnuradio
