They have to be listening all the time if you have voice activation. The mic always needs to be open so it knows when you say “hey siri” or “hey google”. How would it know you said that if it didnt already listen to every word. The question is if that stays local on the device.
Had this explained once, I might miss a detail, but it’s like this:
The only way not to drain your battery is to program in selective key words.
“But then its always listening” yes, but also, no.
Imagine someone speaking into a microphone, and seeing their voice bounce around on a oscilloscope.
You this compresses the audio a LOT, and makes it very difficult to discern the differences between words.
But you if you were trained to notice the pattern for a specific word, like “Siri”, then you could ignore all the other shapes, conserving your battery.
In that sense, yes, they are always listening. But that’s a very small system that only compares like the last two seconds of audio against the stored model of the user saying “Alexa”.
They have to be listening all the time if you have voice activation. The mic always needs to be open so it knows when you say “hey siri” or “hey google”. How would it know you said that if it didnt already listen to every word. The question is if that stays local on the device.
Had this explained once, I might miss a detail, but it’s like this:
The only way not to drain your battery is to program in selective key words.
“But then its always listening” yes, but also, no.
Imagine someone speaking into a microphone, and seeing their voice bounce around on a oscilloscope.
You this compresses the audio a LOT, and makes it very difficult to discern the differences between words.
But you if you were trained to notice the pattern for a specific word, like “Siri”, then you could ignore all the other shapes, conserving your battery.
In that sense, yes, they are always listening. But that’s a very small system that only compares like the last two seconds of audio against the stored model of the user saying “Alexa”.