Alexa is always listening but does not record continuously. It does not send anything to the cloud servers until it hears you say the idle word (Alexa, Echo or Computer). But listening to the waking words is harder than you think.
The echo material is not so smart. Without the Internet, any request or question you ask will fail. Indeed, your orders are sent to the cloud for interpretation and decisions. Amazon does not want all the conversations you have in front of a smart speaker to be recorded, but rather the commands you give to that speaker. For this reason, the company uses a watch word to attract the attention of the smart speaker. To do this, Amazon uses a combination of adjusted microphones, a short memory buffer and a neural network drive.
Adjusted microphones locate your voice
Voice assistant speakers, such as Echo and Echo Dot, typically have multiple built-in microphones. The echo point, for example, counts to seven. This matrix gives the devices several capabilities, ranging from hearing to distant controls to separating the background noise from the voices.
The latter is particularly useful for detecting wake-up words. With its multiple microphones, the echo can locate your position in relation to the sitting position and listen in that direction while ignoring the rest of the room.
You see this in action every time you use the waking word. Stand beside an Echo or an Echo Dot and say the waking word. Notice that the ring lights up in dark blue, then in brighter blue when it circles and “points” toward you. Now move several steps to the side and say the waking word one more time. Notice that the light blue lights follow you.
By knowing where you are, the device focuses better on you and give noises from elsewhere.
Short memory keeps the speaker from overtightening
The echo devices have a lot of storage space, but they do not use a lot of them. According to Rohit Prasad, vice president of Amazon and senior researcher of Alexa Artificial Intelligence, an echo can physically store only a few seconds of audio.
By reducing its capabilities, Amazon not only gives you more privacy (it’s one less place where your voice is stored), but also prevents Echo from listening to entire conversations, which limits it to looking for the word of the day before .
Imagine that you have a three-second tape and a tape recorder. Suppose that after reaching the end, the band goes back to the beginning again and again. If you started recording a conversation, everything you said four seconds ago would be erased and immediately recorded. That’s what Amazon Echo does.
It continuously records but erases everything that it has just recorded at the same time. This short span of attention means that all it can hear is the word “Alexa”, and not much more. Three seconds, however, are sufficient for this word to be recorded, examined and dealt with properly.
Neural Net Training helps with pattern matching
Finally, Amazon depends on neural network training learn how to match patterns. A bit like the others forms of automatic learning, Amazon trains his algorithms by introducing the pending instance of the word Alexa (or Computer, or Echo, according to the waking word that the company forms).
The idea is to cover every inflection and accent, but also the context. Amazon wants your echo to recognize the difference when you speak at when you speak sure or maybe when you talk to a the person named Alexa. Directional microphones also help to achieve this goal.
With each word heard by the echo, the audio passes through layers of algorithms. Each layer is designed to eliminate false positives by looking for sound or context cues. If a layer check succeeds, the word moves to the next one. Finally, when the local device decides to hear the wake-up message, it starts recording and transmitting the sound to Amazon’s cloud servers. Amazon uses four algorithms: one for each wake-up word (Alexa, Computer, Echo) and one for Alexa Guard, which treats specific sounds, such as broken glass, as a wake-up word.
But even in the case of a match, Amazon continues to perform more complex checks. Have you noticed that when someone pronounces the word Alexa in a TV show or advertisement, this usually causes no response from your echo? This is because Amazon is also doing a cloud check.
Cloud checks exclude some false positives
When companies make commercials featuring Alexa, they can submit audio to Amazon. The company runs audio via similar model matching algorithms, used to identify the wakeup word. Once this exact instance is fully cataloged, it is added to a database.
As part of the cloud connection process, your echo includes information about the idle word that it has heard and checks that database. Whenever it finds a match, Amazon will ask your Echo to ignore the wakeup word, turn it off and delete all its recorded sound.
In addition, Amazon searches for the instances of the spoken word simultaneously. Not all companies are submitting audio to Amazon, so she has come up with a new backup solution. After checking the database match, the company compares the wake word fingerprint to all other incoming instances at the same time. It is unlikely that two people who say that Alexa sounds simultaneously sound exactly the same. Therefore, if there is a match, Amazon knows it is a commercial or TV show and ignores the request.
Despite all the checks, false positives still occur. You can listen to what your echo has recorded at The privacy hub of Amazonand you will probably find at least one false positive in the pack. But the technology is constantly improving and ultimately Amazon would like it to work without any alarm clock.
VoiceBrew is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Last Updated: December 2019
The Alexa wake word is what you say to get Alexa’s attention. Want to call Amazon’s virtual assistant Alexa by another name? Just follow the steps below.
2 ways to change the Alexa wake word
You can change the Alexa wake word with an Alexa voice command (faster way) or in the Alexa app if you prefer.
Voice command (20 seconds)
Follow the steps below to change the Alexa wake word for the Alexa device you are speaking to:
- Say “Alexa, change the wake word”
- Alexa will prompt you to choose 1 of 3 other wake word options (Amazon, Computer or Echo)
- Say your new wake word selection
- Alexa will confirm she understood and let you know that you can start calling her by the newly selected name in a few seconds
Pro Tip: If you have multiple Alexa devices, you’ll have to repeat steps 1 – 4 speaking to each device. I recommend using the same Alexa wake word across all of your devices.
In the Alexa app (30 seconds)
- Open the Alexa app
- Select the Devices icon on right side of the bottom menu
- Tap the Echo & Alexa icon on the top left
- Tap the device for which you want to change the wake word
- Scroll down and tap Wake Word under the General section
- Tap the wake word of your choice
Pro Tip: Changes you make only effect the device you tapped in step 4. I recommend using the same Alexa wake word across all of your devices, and you’ll have to update the wake word for each one individually.
Can I pick my own name for Alexa?
Not yet. Unfortunately the only wake word options today are Alexa, Computer, Echo and Amazon.
See Also
VoiceBrew: Get more out of Alexa with a daily Alexa tip delivered to your inbox
I created VoiceBrew to help people get more out of the Amazon Alexa voice assistant. Whether you’re just setting up your first Alexa speaker or smart display or you’re a seasoned pro looking for advanced tips, VoiceBrew can help.
There are so many life-changing ways to use Alexa, but most people aren’t familiar with all of the things Alexa can do. By signing up for VoiceBrew, you’ll receive a free daily email with one actually awesome thing to try with Alexa. VoiceBrew also publishes comprehensive how-to guides on all the best features and important topics like privacy.
Wondering about the best Alexa speakers and smart displays for your needs? Or how to get started with an Alexa smart home? VoiceBrew covers that, too!
@canterrain
July 15, 2019, 6:40am EDT
Alexa is always listening but not continually recording. It doesn’t send anything to cloud servers until it hears you say the wake word (Alexa, Echo, or Computer). But listening for wake words is harder than you might think.
Echo hardware isn’t all that intelligent. Without the internet, any request or question you ask will fail. This is because your commands are sent off to the cloud for interpretation and decisions. Amazon doesn’t want every conversation you have in front of a smart speaker to be recorded, but rather, just the commands you give the smart speaker. For this reason, the company employs a wake word to get the smart speaker’s attention. To accomplish this, Amazon uses a combination of fine-tuned microphones, a short memory buffer, and neural net training.
Fine-Tuned Microphones Pinpoint Your Voice
Voice assistant speakers, like Echo and Echo Dot, typically have multiple built-in microphones. The Echo Dot, for instance, has seven. That array gives the devices several abilities, from hearing commands spoken far away, to separating background noise from voices.
The latter is especially helpful for wake word detection. Using its multiple microphones, the Echo can pinpoint your location relative to where it’s sitting and listen in that direction while ignoring the rest of the room.
You see this in action whenever you use the wake word. Stand to the side of an Echo or Echo Dot and say the wake word. Notice the ring lights up in dark blue, and then a lighter blue as it circles and “points” toward you. Now, move several steps to the side and say the wake word once again. Notice the light-blue lights follow you.
Knowing where you are, helps the device focus on you better and tune out noises coming from elsewhere.
Short Memory Keeps the Speaker from Holding Too Much
Echo devices have plenty of storage, but they don’t use much of it. According to Rohit Prasad, the Vice President at Amazon and Head Scientist of Alexa Artificial Intelligence, an Echo can only physically store a few seconds of audio.
By reducing its capability, Amazon not only gives you more privacy (it’s one less place your voice is stored) but also prevents Echo from listening to entire conversations, limiting its focus to finding the wake word.
Imagine you had a three-second cassette and a tape recorder. Suppose after it reached the end, the tape looped back around to the beginning over and over. If you started recording a conversation, everything you said four seconds ago would be wiped and immediately recorded over. That’s what an Amazon Echo does.
It records continuously but wipes everything it just recorded at the same time. That short attention span means all it can hear is the word, “Alexa,” and not much more. Three seconds, though, is long enough for that word to be recorded, examined, and acted upon appropriately.
Neural Net Training Helps with Pattern Matching
Finally, Amazon depends on neural network training to teach the Echo how to pattern match. Much like other forms of machine learning, Amazon trains its algorithms by feeding it instance after instance of the word Alexa (or Computer, or Echo, depending on which wake word the company is training).
The idea is to cover every inflection and accent, but also the context. Amazon wants your Echo to recognize the difference when you’re talking to it, when you’re talking about it, or, perhaps, when you’re talking to a person named Alexa. The directional mics also assist with that goal.
With every word the Echo hears, it runs audio through layers of algorithms. Each layer is designed to rule out false positives, looking for sound-alikes or context clues. If one layer check passes, the word goes to the next. Finally, when the local device decides it did hear the wake word, it begins to record and pass on the audio to Amazon’s cloud servers. Amazon employs four algorithms: one for each wake word (Alexa, Computer, Echo), and one for Alexa Guard, which treats specific sounds, such as glass shattering, like a wake word.
But even when a match occurs, Amazon still runs more complicated checks. Have you noticed that when someone speaks the word Alexa on a TV show or commercial, it usually doesn’t elicit a response from your Echo? That’s because Amazon also does a cloud check.
Cloud Checks Rule Out Some False Positives
When companies make commercials that feature Alexa, they can submit the audio to Amazon. The company runs the audio through similar pattern matching algorithms used to identify the wake word. Once that exact instance is fully cataloged, it’s added to a database.
As part of the process when reaching out to the cloud, your Echo includes information about the wake word it heard and checks that database. Whenever it finds a match, Amazon instructs your Echo to ignore the wake word, shut down, and discard any recorded audio.
Additionally, Amazon checks for instances of the wake word spoken simultaneously. Not every company submits audio to Amazon, so the company came up with a novel backup solution. After checking for a database match, the company compares the wake word imprint against any other instances coming in at the same time. It’s unlikely that two people who say Alexa simultaneously would sound exactly alike, so if there’s a match, Amazon knows it’s likely a commercial or TV show and ignores the request.
Despite all the checks, false positives do still occur. You can listen to what your Echo has recorded at Amazon’s privacy hub, and you’ll likely find at least one false positive in the bunch. But the technology is continually being improved and, eventually, Amazon would like it to function without a wake word at all.
We’ve got some simple tips you can take to keep Amazon’s Alexa from eavesdropping into your conversations and potentially sharing them. USA TODAY
SAN FRANCISCO— After an Oregon family described the worst fear about owning an Amazon Echo come true — their smart speaker picked up a private conversation and then shared it with the outside world — you might ask: How can I prevent this from happening?
Aside from unplugging your smart speaker for good, there are some safeguards you can use if you’re one of the 40 million people who have these voice-activated speakers from Amazon or competitors Google Home and Apple HomePod.
In the Portland, Ore., family’s case, one of the several Alexa devices they had in their home misinterpreted conversations happening in the house as a command to first record a conversation and then send it as a message to a contact on the father’s contact list.
An Amazon Dot, poised to take a command. (Photo: Amazon)
According to Amazon, Alexa twice asked for confirmation of the requests. The family didn’t hear the requests, perhaps because they volume was set too low, but Alexa heard the conversation — and interpreted the talk as a response to the voice software’s questions. Then it completed what it had determined was a request: Send a message to someone on your contact list.
Here’s the problem: All the digital assistant and smart speaker makers including Amazon, Google, Apple and Microsoft are working hard to make their systems ever-more sensitive, ready to hear the quietest command in the nosiest room and better able to guess the meaning of our sometimes mumbled utterances.
First, though, remember that while Alexa is always listening, it’s not always recording. Amazon’s voice recognition program is constantly listening for its “wake word,” the word that tells the system to pay attention, so it doesn’t record everything it hears.
Only when it hears its wake word does it begin sending what you say to the cloud-computer server, where it’s recorded so it can be translated into commands. Alexa also keeps a record of all the commands you’ve given it so that it can better learn how to answer you.
You can see all the stored commands you’ve given it by going into your Alexa app and looking at settings and then history, where you’ll see all the interactions you’ve had with Alexa. You can also delete this history by going to the Amazon website through the accounts and lists settings.
If you want to minimize the chances Alexa will misinterpret something you say and inadvertently eavesdrop on you, here are some tips:
Set a different wake word
One of the most annoying attributes of digital devices is how often they respond when you’re not talking to them. Then everyone has to clam up until the digital assistant gives up and goes quiet again.
This happens because the assistant either hears its wake word or hears something it thinks was its wake word, and wakes up.
In Alexa’s case, there are four possible wake words — Alexa, Echo, Amazon or Computer. You can test to see which one results in fewer inadvertent Alexa wake-ups in your household. Which one that is will depend on what sorts of things you tend to talk about around the house. You might not want to use “Computer” if you work in a computer repair shop, for example.
Turn up the volume
This is one of those double-edged sword problems. Many people turn down the volume on their Echos because they don’t want to bother others in the household. This can mean that if Alexa says something to confirm a question you might not hear it, especially if you’re not close to the speaker.
Though it’s not clear that’s what happened in the Portland family’s case.
Amazon said in its statement that Alexa said two things out loud during the incident. First, it asked “To whom?” when it thought they were asking it to send a message to someone. Second, it said the name of the person in the contact list the message was going to and then the word “Right?”
However the mother of the Portland family, who reported the incident to KIRO 7 television, said in a follow-up interview the Echo that shared her conversation was very close to her, and the volume was set to seven out of 10. She said it never requested her permission to send the audio.
Say no to Contacts
Many programs ask if they can access your Contacts. Your default should be, “No thank you,” unless there’s a strong reason for doing so.
Alexa’s Calling and Messaging functionality allows you to call or message people in your Contact list who also use Alexa Calling and Messaging. That makes it easy to say, “Call Marion” and have your Alexa call Marion. But it also makes it easy for Alexa to mis-hear your innocent conversation about going to see the fall colors as “Call Calvin.”
Turn it off
You can turn off Alexa’s microphone on the Echo and Dot by pressing the microphone button. This is an actual switch and not just an electronic command, so it can’t be circumvented by someone hacking into the device.
On the Echo Dot and Look, you can also turn off the cameras. Search in the Alexa FAQ on Amazon for detailed instructions.
No voice purchases
Although reports of people accidentally buying things using voice purchase on Alexa are rare, they have happened. You can avoid having to make returns by either disabling Purchase by Voice or setting a PIN number so that only by saying the number can something be purchased. Both can be accessed in the Settings and then Voice Purchasing portion of the Alexa app.
Don’t drop in
One function on Alexa that can be fun is the ability to “drop in” on a permitted contact’s device and hear (and see, with a Show or Dot) the person on the other end. It’s great for friends and grandparents but a little daunting from a privacy perspective.
The system does give warning that someone’s trying to drop in, and you can decline the visit. But if you’d rather they just didn’t come knocking, you can set the Drop In feature so that it only allows permitted contacts, only people in your household or no one at all to drop in.
To set that, go into your Amazon app, click on the specific device you want to set and scroll down to Communications, then set the toggle to the level of availability you want.
Baby steps
Keep in mind how new this technology is — Alexa only debuted at the end of 2014. So many of the kinks are still being worked out, said Yoshi Kohno, a professor of Computer Science and Engineering at the University of Washington.
“When the automobile was first introduced, or the airplane or the computer, it took time for us to understand the good and bad they came with,” he said. “The consequences aren’t all clear yet.”
Alexa is always listening but not continually recording. It doesn’t send anything to cloud servers until it hears you say the wake word (Alexa, Echo, or Computer). But listening for wake words is harder than you might think.
Echo hardware isn’t all that intelligent. Without the internet, any request or question you ask will fail. This is because your commands are sent off to the cloud for interpretation and decisions. Amazon doesn’t want every conversation you have in front of a smart speaker to be recorded, but rather, just the commands you give the smart speaker. For this reason, the company employs a wake word to get the smart speaker’s attention. To accomplish this, Amazon uses a combination of fine-tuned microphones, a short memory buffer, and neural net training.
Fine-Tuned Microphones Pinpoint Your Voice
Voice assistant speakers, like Echo and Echo Dot, typically have multiple built-in microphones. The Echo Dot, for instance, has seven. That array gives the devices several abilities, from hearing commands spoken far away, to separating background noise from voices.
The latter is especially helpful for wake word detection. Using its multiple microphones, the Echo can pinpoint your location relative to where it’s sitting and listen in that direction while ignoring the rest of the room.
You see this in action whenever you use the wake word. Stand to the side of an Echo or Echo Dot and say the wake word. Notice the ring lights up in dark blue, and then a lighter blue as it circles and “points” toward you. Now, move several steps to the side and say the wake word once again. Notice the light-blue lights follow you.
Knowing where you are, helps the device focus on you better and tune out noises coming from elsewhere.
Short Memory Keeps the Speaker from Holding Too Much
Echo devices have plenty of storage, but they don’t use much of it. According to Rohit Prasad, the Vice President at Amazon and Head Scientist of Alexa Artificial Intelligence, an Echo can only physically store a few seconds of audio.
By reducing its capability, Amazon not only gives you more privacy (it’s one less place your voice is stored) but also prevents Echo from listening to entire conversations, limiting its focus to finding the wake word.
Alexa is always listening but not continually recording. It doesn’t send anything to cloud servers until it hears you say the wake word (Alexa, Echo, or Computer). But listening for wake words is harder than you might think.
Echo hardware isn’t all that intelligent. Without the internet, any request or question you ask will fail. This is because your commands are sent off to the cloud for interpretation and decisions. Amazon doesn’t want every conversation you have in front of a smart speaker to be recorded, but rather, just the commands you give the smart speaker. For this reason, the company employs a wake word to get the smart speaker’s attention. To accomplish this, Amazon uses a combination of fine-tuned microphones, a short memory buffer, and neural net training.
Fine-Tuned Microphones Pinpoint Your Voice
Voice assistant speakers, like Echo and Echo Dot, typically have multiple built-in microphones. The Echo Dot, for instance, has seven. That array gives the devices several abilities, from hearing commands spoken far away, to separating background noise from voices.
The latter is especially helpful for wake word detection. Using its multiple microphones, the Echo can pinpoint your location relative to where it’s sitting and listen in that direction while ignoring the rest of the room.
You see this in action whenever you use the wake word. Stand to the side of an Echo or Echo Dot and say the wake word. Notice the ring lights up in dark blue, and then a lighter blue as it circles and “points” toward you. Now, move several steps to the side and say the wake word once again. Notice the light-blue lights follow you.
Knowing where you are, helps the device focus on you better and tune out noises coming from elsewhere.
Short Memory Keeps the Speaker from Holding Too Much
Echo devices have plenty of storage, but they don’t use much of it. According to Rohit Prasad, the Vice President at Amazon and Head Scientist of Alexa Artificial Intelligence, an Echo can only physically store a few seconds of audio.
By reducing its capability, Amazon not only gives you more privacy (it’s one less place your voice is stored) but also prevents Echo from listening to entire conversations, limiting its focus to finding the wake word.
Imagine you had a three-second cassette and a tape recorder. Suppose after it reached the end, the tape looped back around to the beginning over and over. If you started recording a conversation, everything you said four seconds ago would be wiped and immediately recorded over. That’s what an Amazon Echo does.
It records continuously but wipes everything it just recorded at the same time. That short attention span means all it can hear is the word, “Alexa,” and not much more. Three seconds, though, is long enough for that word to be recorded, examined, and acted upon appropriately.
Neural Net Training Helps with Pattern Matching
Finally, Amazon depends on neural network training to teach the Echo how to pattern match. Much like other forms of machine learning, Amazon trains its algorithms by feeding it instance after instance of the word Alexa (or Computer, or Echo, depending on which wake word the company is training).
The idea is to cover every inflection and accent, but also the context. Amazon wants your Echo to recognize the difference when you’re talking to it, when you’re talking about it, or, perhaps, when you’re talking to a person named Alexa. The directional mics also assist with that goal.
With every word the Echo hears, it runs audio through layers of algorithms. Each layer is designed to rule out false positives, looking for sound-alikes or context clues. If one layer check passes, the word goes to the next. Finally, when the local device decides it did hear the wake word, it begins to record and pass on the audio to Amazon’s cloud servers. Amazon employs four algorithms: one for each wake word (Alexa, Computer, Echo), and one for Alexa Guard, which treats specific sounds, such as glass shattering, like a wake word.
But even when a match occurs, Amazon still runs more complicated checks. Have you noticed that when someone speaks the word Alexa on a TV show or commercial, it usually doesn’t elicit a response from your Echo? That’s because Amazon also does a cloud check.
Cloud Checks Rule Out Some False Positives
When companies make commercials that feature Alexa, they can submit the audio to Amazon. The company runs the audio through similar pattern matching algorithms used to identify the wake word. Once that exact instance is fully cataloged, it’s added to a database.
As part of the process when reaching out to the cloud, your Echo includes information about the wake word it heard and checks that database. Whenever it finds a match, Amazon instructs your Echo to ignore the wake word, shut down, and discard any recorded audio.
Additionally, Amazon checks for instances of the wake word spoken simultaneously. Not every company submits audio to Amazon, so the company came up with a novel backup solution. After checking for a database match, the company compares the wake word imprint against any other instances coming in at the same time. It’s unlikely that two people who say Alexa simultaneously would sound exactly alike, so if there’s a match, Amazon knows it’s likely a commercial or TV show and ignores the request.
Despite all the checks, false positives do still occur. You can listen to what your Echo has recorded at Amazon’s privacy hub, and you’ll likely find at least one false positive in the bunch. But the technology is continually being improved and, eventually, Amazon would like it to function without a wake word at all.
If you have an Amazon Echo device, then you’ve likely gotten pretty used to saying “Alexa” whenever you want it to do something.
While the device defaults to using ‘Alexa’ as its wake word out of the box, there are some situations (for instance, if your name is Alexa) that you might want to change things up and use something different.
Manage Kitchen Chaos With Alexa’s Named Timers
Alexa and Google Home both allow you to set multiple, named timers, and they will save…
Amazon won’t let you change your Echo’s wake word to anything you want, but it does offer a few options. Instead of “ Alexa” you can also use “Echo” or “ computer” as your wake words. It’s a feature that’s been available for a while, but not many people realize it’s there. CNBC pointed it out again this weekend.
To make the change, go to the Alexa app on your phone and then tap the hamburger icon on the top left side of the page (it looks like three lines stacked on top of each other). From there, select Settings and then Device Settings.
The wake word you choose is device specific, so if you have multiple Echo devices you’ll need to swap things out on every single device you have that you want to be changed individually.
When you tap on a device, you want to scroll down to “Wake Word.” Select the new wake word you’d like from the list, and then select “OK.”
You can also make the change directly on an Amazon Echo device with a display. On those, say “Go to Settings” and then select “Device Options” followed by “Wake Word.”
And keep in mind your device will need to be connected to the web to make this change, so if you have an Echo device unplugged for some reason, you’ll need to plug it in before you can make any adjustments.
Emily is a tech, travel, and alcohol reporter based in San Francisco. She is also the author of the book “Productivity Hacks: 500+ Easy Ways to Accomplish More at Work–That Actually Work!”
Share This Story
Get our newsletter
DISCUSSION
Drat, and here I was hoping I’d be able to start calling it Chickenfucker.
With the evolution of Natural Language Understanding, number of devices came in the market like Alexa, Google Assistant etc. These devices get activated with the wake word. A wake word is a special word like “Hey Siri”, “OK Google”, and “Alexa”, which activates the devices. Wake word also known as ‘hotword’, ‘trigger word’, and ‘wake up word’ are the phrases which help end users to initialize the devices.
After invoking wake words voice assistant’s records commands from the invoker (user) and acts according to its command. It separates the background noise and act as per instruction.
Types of Wake Words:
There are two kinds of wake word detectors: Universal and Personal.
The Universal Wake word is common for all, actually it is trained over a variety of voices. The model in which it is trained is mostly neural nets. It can be activated by anyone who invokes it. If we compared it with personal wake up words, they are customized and trained locally.
The Universal does not allow random wake words while personal does, though both of them are fed into machine learning.
There are multiple technologies working together which activates wake-up word.
- Listener – There is a number of microphones which listens the wake up word. They filter out the background noise, differentiate between wake up words and others and activate the device. After listening to the voice it also follow the direction from where this voice is coming.
- Built-in Memory – It has a limited memory which normally retains for three seconds to collect the inputs from the user, process it, and delete the data after getting new input. This gets written old data.
- Data Processing- This is done by feeding the input to a series of neural nets which understands the human requirements and responds to it accordingly. Every word it hears passes through multiple layers of testing. This testing determines if the word is the wake word. After the word passes through several layers of verification, and the device evaluates that it was actually the wake word, so that it can start recording.
Performance of Wake word recognition:
We can see or measure the performance of Accuracy of wake word recognition by evaluating the feature like, it should not start recording without someone directly speaking to it. Recognizing the word and not getting it confused with other words is a top priority. The software relies on data that represents every possible way to say the wake up word. This data helps the device determine when the user is speaking to the device. It has to ensure it doesn’t activate by hearing the word in casual conversation or background noise.
Using neural network, device does not start recording when the word Alexa is found in background noise. If someone says, “wake up word,” during a television program, the network should understands that it is not likely that a large number of devices all heard the same word, in the same tone, at the exact same time. It will ignore the sound and not begin recording.
Available wake word systems in the market
a) Raven: This system is based on the Snips Personal Wakeword Detector and works by comparing incoming audio to several pre-recorded templates.
b) Porcupine: Porcupine is a highly-accurate and lightweight wake word engine. It enables building always-listening voice-enabled applications. It is
- using deep neural networks trained in real-world environments.
- compact and computationally-efficient making it perfect for IoT.
- cross-platform. It is implemented in fixed-point ANSI C. Raspberry Pi (all variants), Beagle Bone, Android, iOS, watchOS, Linux (x86_64), Mac (x86_64), Windows (x86_64), and web browsers are supported. Furthermore, Support for various ARM Cortex-A microprocessors and ARM Cortex-M microcontrollers is available for enterprise customers.
- scalable. It can detect multiple always-listening voice commands with no added CPU/memory footprint.
- self-service. Developers can train custom wake phrases using Picovoice Console.
c) Snowboy: Snowboy is an highly customizable hotword detection engine that is embedded real-time and is always listening (even when off-line) compatible with Raspberry Pi, (Ubuntu) Linux, and Mac OS X.
Snowboy is:
- highly customizable allowing you to freely define your own magic hotword such as (but not limited to) “open sesame”, “garage door open”, or “hello dreamhouse”. If you can think it, you can hotword it!
- always listening but protects your privacy because Snowboy does not connect to the Internet or stream your voice anywhere.
- light-weight and embedded allowing you to runs it on Raspberry Pi’s consuming less than 10% CPU on the smallest Pi’s (single-core 700M Hz ARMv6).
- Apache licensed!
Currently, Snowboy supports:
- all versions of Raspberry Pi (with Raspbian based on Debian Jessie 8.0)
- 64bit Mac OS X
- 64bit Ubuntu (12.04 and 14.04)
- iOS
- Android with ARMv7 CPUs
- Pine 64 with Debian Jessie 8.5 (3.10.102)
- Intel Edison with Ubilinux (Debian Wheezy 7.8)
d) Pocket sphinx: one of Carnegie Mellon University’s open source large vocabulary, speaker-independent continuous speech recognition engine.. This is an early release of a research system.
@canterrain
Updated September 23, 2020, 10:20am EDT
Amazon just rolled out Alexa Guard to all Echo users. Your Echo can now listen for breaking glass, alert you to smoke alarms, and randomly turn your lights on and off. But it’s not a full security system.
What Is Alexa Guard?
Alexa Guard is a new free service from Amazon for Amazon Echo users. When you enable Guard, your Echo devices start listening for the sound of glass breaking or smoke and carbon monoxide alarms. If an Echo detects any of those noises, it will send you an alert.
Amazon accomplishes this feat by altering the wake word behavior for your Echo devices. Usually, your Echo listens for “Alexa” (or one of the optional wake words) to activate. But enabling and activating Guard mode adds additional “wake words” that match up to the sound of glass breaking and alarms. In other words, your Echo listens for these sounds just like it listens for “Alexa.” When you deactivate guard mode, your Echo returns to its standard behavior.
Beyond listening for trouble, Guard can take some basic preventative actions. If you have smart lights tied to the Alexa platform, Guard can turn them on and off at random intervals to give the appearance that you’re home. You choose which smart lights are automated, so your basement light isn’t turning on and off pointlessly.
Once enabled, you arm Guard by telling Alexa “I’m leaving” and disarm by saying “I’m home.” Your Echo will say it’s starting or stopping guarding. You’ll receive an Alexa notification on your phone, too.
Alexa Guard Isn’t a Monitored Security System, But it’s Helpful
Alexa Guard isn’t a monitored security system. Amazon spells that out multiple times in its FAQ:
Alexa Guard is not a replacement for an alarm system or life safety device and cannot contact emergency services, such as the police or fire department, on your behalf. Smart Alerts are provided for informational purposes only.
This is something to keep in mind. Alexa Guard won’t contact the police or fire department for you. For example, let’s say you’re at the theater and your phone is set to do not disturb. If your house catches fire or a burglar smashes all your windows, you won’t receive the notifications. It may be too late to notify the police or fire department by the time you do see the notifications.
If you’re looking for a security system with monitoring services, you may want to consider SimpliSafe or Amazon’s Ring Alarm System.
But, chances are, you don’t usually keep your phone on do not disturb when you leave the house. If you don’t have any security system at all right now and you have one or more Amazon Echo devices in your home, this could be a step up from your current situation.
Smoke alarms are an essential part of every home, but they do little good when you leave home—unless you spend over $100 per unit replacing your existing alarms with a smart version like Nest Protect. With Alexa Guard, you have a chance of being notified about a fire or a home intruder with just an Echo. Should your Echo have a camera (like the Echo Show), you can use the Drop In feature to see what’s happening before calling emergency services.
Home security is just as much about prevention and reaction. Deterring a home invasion is better than interrupting one. That’s why security systems encourage you to put out a “Protected by” sign: thieves prefer the lowest hanging fruit. Guard’s smart light integration makes it look like you’re home, and that’s helpful.
Some Security Systems Work with Guard
While Alexa Guard isn’t a security system itself, it can work together with some monitored security systems. Guard can forward your alarm notifications to your security service—along with recorded audio—if you choose to enable this option.
Your security service will take the information and then act on it as the company deems appropriate, whether that be contacting you, calling emergency services, or both. Amazon says Alexa Guard is compatible with Ring and ADT monitored services. Others may be compatible as well.
It’s a good idea to get in contact with your security system to learn if it works with Alexa Guard and what steps are necessary on your part.
How to Use Alexa Guard
Before you can arm and disarm Alexa Guard, you have to enable it. Start by opening the Alexa app on your phone. Tap the hamburger menu in the upper left corner.
Tap “Settings” in the menu sidebar.
Scroll down the list of options until you see “Guard” and tap on it.
Next, tap “Set Up Guard,” and you’ll be prompted to enable glass detection, smoke detection, and smart light randomization. Tap “Add” for each thing you want to enable.
After you enable randomized smart lights, provide your ZIP code (to determine when sunset is) and choose which lights to randomize. You’ll find some lights selected automatically. Check any you want to add and uncheck any you don’t want in the rotation. Tap “Continue” once you’ve chosen your lights.
Finally, tap “Confirm” to finish the setup process.
When you’re ready to leave the house, say “Alexa, I’m leaving,” and Alexa Guard will arm. When you get home tell Alexa “I’m home” and Guard will disarm. You’ll receive notifications on your phone when Guard turns on and off.
Once you understand what Alexa Guard does, it’s quite powerful. Without having to buy glass breaking sensors or smart thermostats, you get on-the-go notifications from your home. It won’t solve every worst-case scenario. But, whether or not you’re using a monitored security system now, it can give you some extra peace of mind.
