Re:Voice Calls: Secure, Crystal-Clear, AI-Powered
by CodeMichael on Thursday March 30, 2017 @11:14AM
(#13996079)
Correct, last article I recall reading about deciphering VBR from packet size alone was something in the neighborhood of 50% success rate.
[ Parent
| on HN ]
Re:Voice Calls: Secure, Crystal-Clear, AI-Powered
by Y_Y on Thursday March 30, 2017 @11:40AM
(#13996321)
Then why not compress really efficiently by just transmitting packet sizes?
Re:Voice Calls: Secure, Crystal-Clear, AI-Powered
by c22 on Thursday March 30, 2017 @12:38PM
(#13996864)
Because 50% of them won't be understood?
Re:Voice Calls: Secure, Crystal-Clear, AI-Powered
by e12e on Thursday March 30, 2017 @02:14PM
(#13997607)
On the other hand, if you could do it, you'd probably have invented a convoluted speech-to-text (where text is a index into a dictionary of words). Note that you would also likely lose things like inflection, voice, accent etc - so while it might work as a texting system with voice input - it would be a poor substitute for voice chat..