How to Compare two wavs 500 points

Hello everybody,
I am doing a program to improve pronounced words in other languages, what is missing is:

A way to compare two wav words. See how the system works

First the user click on one button
     A word is pronounced like - mother
after listening the word, the user clicks on other button and he repeats the word spoke.

After finished the system compares the two wav file and gives a graphic of comparison.

I don't know how to make this.

I need a help
Alexandre
LVL 1
hidrauAsked:
Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.

gwalkeriqCommented:
It is likely that you need far more human than you realize.

You should check out this site, http://www-speech.sri.com/, which is related to speech research topics and look at this paper http://www.asel.udel.edu/icslp/cdrom/vol3/670/a670.pdf to get an idea of what you are facing (paper is in English, but it is re: French pronunctiation analysis). The paper includes several references that lead to further information.

I think this would be an incredibly hard topic to cover in a forum such as this.
GwenaCommented:
I think this would be VERY difficult to do...

I think what I would consider is to just let the user
record his repeated word...and then play the original followed
immediately by his version..so s/he can compare the two.

For the computer to reliably compare the two and produce an
accurate graph of the results would be about as difficult as
bringing peace to the Middle east :-/

_Katka_Commented:
Hi, Alexandre :)

The most exciting I had found is Dragon NaturallySpeaking SDK it supports Delphi:

http://www.voicerecognition.com/products/dragon/developersuite.html

but I guess it's commercial..anyway it looks like you should be able to
record your own vocabulary and compare the samples.

regards,
Kate
Rowby Goren Makes an Impact on Screen and Online

Learn about longtime user Rowby Goren and his great contributions to the site. We explore his method for posing questions that are likely to yield a solution, and take a look at how his career transformed from a Hollywood writer to a website entrepreneur.

billtouchCommented:
The math you are looking for is FFT. You need to reduce the many various waveforms in voice sound to something recognizable. That is about all I can answer on the subject.

Maybe you can contact Worcester PolyTech Institute (Worcester, MA) or MIT (Cambridge, MA). They do tremendous audio research. As example, these are the only schools from which Dr. Bose hires.

You
hidrauAuthor Commented:
Hello everybody
As I can see each of you has a different answer for me. I know that the question is not easy and is very complex too. But sometimes you can find some answers in the internet what demand a lots researches.

I will leave this question opened for more one week and the better answer will take the points.

Thanks for the moment, I will take a look in all link posted here.

Alexandre
billtouchCommented:
I have been trying to find theoretical audio people to help me solve one of my problems. Of all the disciplines, this seems to be one of the least populated. Published works on this are rare as well. You have to be in the library of one of the two schools I mentioned above. I found a few white papers covering similar topics but the people that wrote them are now in the employ of Bose, thus cannot help me.

There is a project being sponsored by the National Security Agency (NSA) at Ft. Meade but I cannot find out who is working on it. My understanding is that they started with some published code.  I have no time to do a search, but outside of universities, the only place that would have such code is NIST (www.nist.gov). Its a pretty cool place. They cover (and sponsor) most of the theoretical research going on in the country.

Recently, there is a push to make use of audio in security applications. I used to know someone who worked in the Maryand complex. I wil try to contact him and see if he has some suggestions .

Beyond that, good luck :)

Bill

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial
It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today
Delphi

From novice to tech pro — start learning today.