Continue to Site

Welcome to our site!

Electro Tech is an online community (with over 170,000 members) who enjoy talking about and building electronic circuits, projects and gadgets. To participate you need to register. Registration is free. Click here to register now.

  • Welcome to our site! Electro Tech is an online community (with over 170,000 members) who enjoy talking about and building electronic circuits, projects and gadgets. To participate you need to register. Registration is free. Click here to register now.

Voice Recognition

Status
Not open for further replies.

builderz

New Member
I am using a mega32 to enable voice recognition in my robot. im confused about fingerprint generation and comparing of fingerprints in voice signals.
 
Well, I haven't gone that far in making anything similar. But just think about voice as soundwaves with certain patterns. Typically you record the same sound/s repreatedly and try to find changes in frequency, amplitude, etc and see if there is a correllation. Then look for certain spot/s that change. Then you try to make a record of those spots that change as a pattern to look for. Then the next time the system hears that same sound it looks it up in a table and tries to match it.

There are numerous ways that chips do this. Most require lots of A/D sampling and lots of processing power.

Now unless you're planning on spending most of your controllers cycles trying to do this you might be better off on connecting a chip that will do most of that work for you and let the controller decide what to do with the results instead.

Michael
 
Status
Not open for further replies.

Latest threads

New Articles From Microcontroller Tips

Back
Top