If you replace "fuzzy human speech-command detection" with "buttons which can accidentally be pressed" - how is this different from butt-dialing?
The main reason I won't have any of those products in my house is because of that. I'd much rather have a confirmation of some kind before the system takes action.
"...random talking..."
Assistant "I am recording"
Me: "Stop recording"
It might be a bit awkward at first to do that in front of strangers, but once it catches on, that will wear off. ;-)
Entering the pattern after it's locked is pretty much impossible though.
Also, the case adds to the pressure needed to depress the button anyway.
This sort of thing makes me nostalgic for the old days of explicit "Save" commands in every application.
And once you have Undo, it's nice if you always have Redo, in case you Undo once too many.
But it'd certainly be good with more feedback.
thats not foolproof but much better than what we have now, and i think we are pretty close
Phonetics is hard. Especially with ambient noise, echo and such. I had a conversation with one of the speech engineers when I worked at a speech recognition company and the level of detailed problems to solve was impressive. Totally made sense after talking about it, but things I would not have thought about before.
I'd imagine the next thing to come in this area that would really make an improvement is an "on person" microphone. Maybe it's a pen in your pocket, or some kind of vibration detection (that could pick up the wearers voice), that would then allow some improvemnts in the domain of "who is talking" and how well the voice is processed.
Both of these technologies work in nightclubs and fighter jets. I assume they are very high SNR, as far as ambient noise is concerned. The subvocal one might just be a phonetic/intonation input, which then requires voice synthesis if actual voice is the goal.
An alternative, "wireless" approach to near-perfect security would be to invent-plement some kind of vocal, human-executable GPG/TLS.
It doesn't even need to get good audio - just enough to give a bit of an indication that what the device picked up was me talking and not random noise and ideally some way to somewhat correlate it to the audio the device picked up to give it an indication it was me it heard. It'd also give you the option of setting the devices to require confirmation for certain types of orders if they were not confirmed by an authorised device, or if they were not confirmed by a device (so you could let people present give instructions but not some random joker on voice chat in your online game for example).
If we could get support for that into e.g. a watch, it'd be very much useful.
I believe any implementation of security through acoustic biometrics would be vulnerable to replay attacks.
Systems to reproduce acoustics with high fidelity are commonplace - You might be using the output component of such a system right now if you're listening to music.
You could make the Assistant remember the exact fingerprints of all previous activation phrases and only trust you if it was original. This could be circumvented if you spoke the activation phrase at any point where your assistant could not hear you, for example to another Assistant of the same brand.
Audio is definitely too easy to spoof for it to be a security method IMO.
it may have a place in security as well but i can only see it as part of a much more holistic model
This is exactly how the Google Home works right now.
I can, however, say "Hey Siri, call 867-5309." Or "Hey Siri, Facebook status: my anus is bleeding. SEND!"
Because we are apparently incapable of applying past lessons to new technologies.
My point is they're really half-assed products right now that are behaving badly/immaturely.
Serves me right for having screen reading on near my phone.....
(jk, jk, but seriously though)
And if their management is anything like my management, they go ahead and release it anyway.
The only problem here is that Google still doesn't recognise my voice half the time, perhaps because I'm never sure about how I should speak to an inanimate object.
Speaking of unlocking methods, face unlock appears to no longer be available as an option for me. I can't find it in settings anymore (smart unlock etc).
b) There is a great deal less ambiguity around "pressing buttons" than there is around interpreting speech. While it is unlikely that your phone will incorrectly detect button presses, it's very common for voice-activated devices to a) incorrectly detect a wake word (either negative or positively); and b) misunderstand some particular word used in the command. Your phone is not going to think you pressed the "Clothes" button when you actually pressed "Close".
c) The entire functionality of the device is accessible from behind that big ambiguous interface. On a phone, there are many distinct steps and screens to step through when you want to do something (this complex interface, by the way, is a non-trivial part of why butt-dials are quite rare these days). On a "smart speaker", most things are just one misheard statement/command away from occurring.
Does having the device programmed to make mistakes make it more comfortable to use, because we know humans are infallible too.
whats the analogous behaviour for alexa?
also remember these are shared devices in a home, not a personal device in your hand. could i shout into somebody's window, "hey alexa send my browsing history to bob@hotmail.com"!
While you may have never pocket dialled, plenty of people have. I've received more than a few accidental calls in the past.
I equate this to some phone users placing their devices hanging over the edge of tables - as if they don't care about them hitting the floor. Should phone makers toughen their phones and should Amazon improve Alexa anyway? Sure.
https://www.safety.com/wp-content/uploads/2017/06/mute-butto...