Re:Google speakers are listening to more than just voice com...
by scollet on Saturday August 08, 2020 @10:52PM
(#24096908)
For anyone curious about this, I highly recommend developing on CMU Sphinx for a weekend project. It will really paint some pictures about machine interpretation based on training data and the actual application code.
Even when they actually do ship audio off the device for processing, I'd be surprised if it's done losslessly.