It's not true anymore, but Alexa's used to only listen for specific keywords using a low-energy local-only chip.
It has since changed, as stated, and I have to assume other vendors followed suit.
A community for those that would like to get away from Google.
Here you may post anything related to DeGoogling, why we should do it or good software alternatives!
Be respectful even in disagreement
No advertising unless it is very relevent and justified. Do not do this excessively.
No low value posts / memes. We or you need to learn, or discuss something.
!privacyguides@lemmy.one !privacy@lemmy.ml !privatelife@lemmy.ml !linuxphones@lemmy.ml !fossdroid@social.fossware.space !fdroid@lemmy.ml
It's not true anymore, but Alexa's used to only listen for specific keywords using a low-energy local-only chip.
It has since changed, as stated, and I have to assume other vendors followed suit.
As a specific example, the ESP32 chip does low power voice recognition for pre-trained trigger words. This lightweight recognition lacks the training to detect anything other than the list of trigger words that Espressif provides.
Basically only battery-operated devices work this way (for power consumption reasons). If you’re plugged in you’re probably always running the high quality listening loop.
This is also why a lot of the wake words are similar:
Those all have different vowel sounds, hard consonants etc. because without that there's not enough difference to make a unique wake word/phrase. Google needed something like "Hey" or "OK" before it because "Google" itself doesn't generate enough unique sounds to act as a keyword. They're also between 3 and 5 syllables because they need to be short enough to monitor for them, and long enough that they can be distinguished reliably from background noise.
The sounds are converted into MFCCs, which is sort-of an extremely lossy form of compression. It was originally used to identify numbers, like when someone would call into an automated switchboard and they'd have to say "one" or "five". It couldn't identify complex words, just distinguish between a small set of very different sounding numbers.
The way these systems work is that they're running on a very low-power loop converting ambient sounds into these patterns and seeing if there's a match for a wake-word pattern. The sound is converted into basically a time vs. frequency matrix and matched against the keyword / phrase. If there's a match it unlocks the much more computationally-expensive voice transcription programs, otherwise it just throws out the data.
You can tell that at least mobile devices aren't always listening because if they were actually doing full-on voice transcription all the time, the battery would drain much faster. If they were doing off-device voice transcription, the antenna would have to stay on a lot more, which would also kill the battery, and it would be visible in your bandwidth bill.
People need some more basic computer literacy. I get that the FAANG companies are "evil", and want to do unscrupulous things with your data, but there's often a simpler explanation that doesn't involve massive privacy violations that security researchers would have caught long ago.
Even in the first scenario, what stops there from being multiple wake words with different functionality? So like "ok google" wakes up the bot but "pepsi" wakes it silently and has it tick a box on the back end of a server that now sends me Coke adds because they paid about $3.50 for the privilege?
Pretty much nothing. Any company with the resources of Google or Amazon could easily have their top 100 wake words trained into that model.
Hey, wiretap
On a side note, if you have a Chromebook or other laptops/desktops, you can reformat the BIOS to give you better control, more security, and less backdoors.
Last I muted mine it did this still. I believe the rationale is that wake word detection is local
I plan on moving away from the ecosystem but haven't yet been able to invest time and money in a home assistant setup and start thinking about migrating
(I know many feel smart home tech is frivolous and just a security risk and privacy violation- I use automation to help manage a disability/medical condition)
I have been very happy with local stuff. I have home assistant running on a pi, independent of my main server (cause I wanna control the lights easily while changing server hardware).
All my smart devices (lamps, mostly) use Zigbee, and it's just way easier and more flexible than classical dimmers. There's local voice recognition support, but for that I'd probably run it on something with more horsepower than a raspi.
Yeah, I've been planning to set up a smart light switch in my kitchen and if/when I eventually get to that I'll be setting up a home assistant install on a little thin client and using ZigBee instead of a WiFi device directly connected to google home. That way I can start to play with automation in haos and start connecting all of my existing wifi devices through haos on my own hardware.
I'd like to transition everything to offline protocols running locally, its just kind of a project and takes money. A while back I was doing my research for it and I think I decided on hardware, but haven't gotten further than that, I just kinda have too many expenses and projects on my plate for the moment
I'm looking forward to all the tech stuff I depend on being actually my own in the future though :)
Yeah, totally understand that. Had an easy start cause I got a lot of Philips Hue stuff for free from a friend who got fed up with smart tech in general. He now has a Pixel with mostly blank Graphene and a Raspberry Pi as his only computing devices, lol.
I had a lot of fun programming click patterns for smart switches that are incomprehensible for anyone but me XD
Good luck with your transition~
Why are we ai upscaling so many things???? Like what does that playdoughy smoothness add to anything. Espescially 10 year old memes 😭
(i dont blame op, anybody still using google or unaltered ddg will get ai for their first like page or two of image results)
You muted yourself from the conversation, but it still listens for commands.
Also, I love how every time "microphone" is mentioned on social media, the social media/spyware sockpuppets come out and say "well aktually..." and put this word vomit all over the place hoping you'll just roll over and accept it. Must be a nice paycheck to cash...