Jump to content
Electronics-Lab.com Community

Voice-Activated Door Opener



Recommended Posts

Hey everyone! ;D I'm a newbie here! There is this one project I am currently trying to work on and I need some help. When I was searching though the projects on this site, I found the voice-activated switch. Now, my project is to make a voice-activated door opener for my rec room. I was curious as to weither the voice-activated switch could somehow open the door, and if anyone nows a way it could open it, to help and explain to me! I'm new at this kind of stuff and I really need the help! Thanks :)!

Mallory

Link to post
Share on other sites
  • 2 weeks later...

Yap, Iam a newbie also but I have similar interests in voice and smart card activated/driven systems.

Now,I contribute;
Source = Voice - reverb, pressure, frequency range etc
Recieved by: Sound sensor/ Membrane eg microphonelike device
Logic - Decrypt sound for the matching sound -in this case Voice - pattern or so
Action- Based on an algorithm like if (voicepatternrecieved ISEQUALTO John's voicepatternstored ) Then Opendoor
Next: Some gears/ servos etc move to unlatch the door.

I consider something more detailed to enable some progress.
I hope this is useful for now

Link to post
Share on other sites

if it is just a sound activate door opener, then you can use a relay and a electronic lock and a sound activate circuit.

However, if you want to have voice recognition, it will be a much more difficult one. It will be another issue. Most likely, you need a fast processor or even a PC to do so.....

Link to post
Share on other sites
  • 2 weeks later...

Well using a PC makes the job PC based. And may be some sort of waste cuz I intend to learn by doing as a newbie. Why not use some microcontroller like a DSP or PIC. They act like some RISC microprocessors and I think can do a lot of logic. So you could store pre-recorded voice parterns maybe on another chip for comparison with the incomming voice pattern. Also, human voice should be between 1K and 3K so a Bandstop filter should filter after the microphone.

Link to post
Share on other sites
  • 2 weeks later...

Thanks for your contribution.
I am just back from prevewing the link. That will be a very good addition in
1. prompting users
2. And possibly reversing the analogue voice input into text for processing ie working the chip backwards. I don't know it that will be possible.

Importantly, I have just had a glimpse of Bascom AVR code, looks very simple and appealing in Basic. I hope programming PICs is going to be that simple.

Link to post
Share on other sites
  • 2 weeks later...

Thanks for your contribution.
1. Maybe a VU meter will display the amplitude of the recorded voice say at a predetermined value displayed visually to the user. Such that upon second use - attempt to use voice activation, the user will use the visual VU meter to guage the amplitu de / loudness of his input voice signal. ::)

2. Another way, may be to trim via software what ever input comes. OR using some f orm of pattern matching (pardon my using the term here) assuming every voice signal has a unique pattern that can be obtained and stored. Thus irrespective of the amplitude -shout or groan the pattern should be CONCEPTUALLY/THEORETICALLY THE SAME ;D

PLEASE correct me if I am wrong.

Link to post
Share on other sites
  • 4 months later...

Been looking for this topic for hours.
Finally, here I am. Well there is a chip or so RSC-364 I found on my PC from last year. It - uses neural network to match on chip speech recognition and accuracy of >97% for speaker independent and 99 for speaker dependent recognition

www.sensoryinc.com
Hope we may have solved that part of the project with this.

Link to post
Share on other sites

Hi Garvey,
You may want to contact that company and ask their pricing for 1 or 2 chips. They say $2.40 and $3.85 in quantities of 100K but you won't be using anywhere near that amount. It might be too costly.

Do you care if different people can say the phrase and gain entrance? Or can it be anyone to say the command?

Assuming the IC is too expensive. Here is what you could do.

For different amplitudes, you could record the signal to memory, scale the signal to its maximum (ie if they said it quietly it would still use the full range).

You may also have difficulty with people talking slower or faster. To solve this, you would need to "shrink" or "stretch" the signal to fit the same length. To do that, you will need some sort of indicator to tell the person when to speak (like a tone). That lets you line up the signal to be compared with the one in memory. I don't know how you will determine the end of what they are saying.

Following all this processing, you then perform a correlation between the pattern signal and the signal just entered into the system. You do this by multiplying each sample together (which is why they should be the same length), and then adding all the multiplications together. This step is what typically kills the system because all those multiplies is processor intensive. Following the correlation, you simply need to "tune" the system (ie if the correlation is over X then open door, else, quit). The lower you make X, the more likely the door will open for any noise. The higher, the door will not open at all for any sound.

I believe this method will have problems discriminating between different people though. You can use fuzzy logic or a neural network algorithm to get more specific.

Hope some of that helps.

Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

Loading...
×
  • Create New...