Correct me if I'm wrong, but couldn't a possible fix (or at least improvement) be to run the audio command through a compression algorithm such as MP3 before passing it to the AI for analysis, thereby stripping out a significant portion of human-inaudible sounds?
amazon needs to fix this now, and it may not be easy.
h/t @AndrewSundstromhttps://www.fastcompany.com/90240975/alexa-can-be-hacked-by-chirping-birds …
-
-
-
Low pass filter. Pretty straightforward with DSP.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.