Larry's Blog

SUCCESS WITH A/D !!

I set up a circuit using one of my PIC microcontrollers to control an ADC0804LCN analog to digiital conversion chip. I measured the voltage on 2 AA batteries I had lying around. When I measured the batteries in series with my voltmeter, I got 2.81 volts. So after considerable circuit debugging and also debugging of my simple PIC program called ADPGM.ASM, I got the output which for the time was displayed in 8 LEDs. The output was as follows:
---MSB----------LSB
----1 0 0 1 0 0 0 1-----
In decimal that is 145. So:
-----145---- ---X-----
------------ = ---------------and X = 2.84
-----255--- ----5-----

Not bad ! My A/D chip can make a conversion in 100 usecs. So if I allow about 25 usecs for my computer pgm to store each sample voltage of an incoming signal, I could take 8000 samples a second !!!! Of course, my PIC program controls the number of samples I choose to take. I will be using this A/D converter to analyze speech and compare spoken words to some kind of template for comparing and identifying the words.

POSTINGS IN YAHOO & GOOGLE GROUPS

I have been posting info about my current project with emphasis on the SPEECH RECOGNITION aspects. Here is a posting I put out on YAHOO.

In my latest project utilizing several PIC microcontrollers, I need to have
communication between the system and the user - who may be a random
operator - say at an exhibit. Besides LCD's and other types of displays, the
computer will communicate with a menu of voice messages using a
Chipcorder. But I want the operator to reply in a small vocabulary of spoken
words - IWR they call it - isolated word recognition.

Now I am beginning to learn there are a number of chips out there called
VPRs - voice recognition processors.

However, I want to try my hand at the nitty-gritty of speech recognition
circuitry myself. I am learning about A/Ds and DACs and I want to use a mike and an amp and digitize some individual words and see what the templates of the
sigs looks like. Then I would like to develop algorithms for comparing one
digitized template against another. Sound like fun to anyone?

Why let those engineers who developed these VRPs have all the fun? I like to
hear if anybody has tried one form or another of speech recognition.

SPEECH RECOGNITION

Well, I was looking for a new project, and decided I would use several PIC microcontrollers connected together. There would be some kinds of displays which would show menus to the users But the main thing would be that the computer would talk to the user, and the user would reply by voice.

So I have already mastered using the Chipcorder with which the computer can voice a variety of messages. But I also want the computer to be able to recognize "yes", "no" and maybe up to a dozen words and numbers.

So what is SPEECH RECOGNITION ?

Well, it entails accepting words spoken into a microphone, which will then be somehow processed electronically. So the analog sounds can be amplified and some kind of comparison made with a previously recorded template of some kind. One approach is to identify phonemes of which there are about 40 in the English language. Phonemes are the basic vowel and consonant sounds like oo,ah oh,ee, uh and k,t,p,ch,z,s sounds. Now I suspect my best tool for speech recognition will be DSP (digital signal processing). This involves changing the analog sounds to digitized form. It has been found that any analog values like
temperature, pressure, voltage can be processed much more effectively when they have been digitized. One computer byte of data has a binary range of value of from 0 to 255. So 2.5 volts on a scale of 5 volts might become a byte value of 127. After computer processing, the values can be changed back to regular voltage values.

So with analog sounds, we can digitize by taking numerous samples of the familiar waveforms. Sometimes it is hard to believe that the sounds of an entire symphony orchestra can be carried in a complex analog wave form. This sound
can evidently be effiiciently sampled and digitized as we realize when we listen to music on our IPOD.

I plan to experiment using my PIC microcontroller to sample sound signatures and find ways of comparing the digitized templates. It may even get to a case of pattern recogniton, since you can hardly expect to find exact matches. But it will be fun seeing what I find out.

I have already found there is a 40 pin speech recogniton chip for about $10. I may eventually wind up with something like that, but even setting that up will be very challenging as far as hardware and software implementation.

I'll let everyone know if I am having fun with this next project.

GRAPHIC LCD IMAGES

Here are some images I've generated on my
64 X 128 Graphic LCD