|
-
Mar 10th, 2002, 04:14 PM
#1
Thread Starter
New Member
*****Urgent Project*****
I am trying to create an application for recording voice passwords and only allowing the same person to login by speaking the same word.
I have had some success but the problem is the accuracy of the program.
I am willing to pay and have little time left for completion of this project...just under 5 days actually and need to have a finished working application for demonstration then, anybody who can program this without using M/softs speech recognition as this is not accurate enough please get in touch asap.
Basically the user needs to speak one word that the computer will recognise that user by and no one else.
Help!!! I look forward to a speedy response from all the experts out there.
Nordek
-
Jun 5th, 2002, 04:40 AM
#2
New Member
Re: *****Urgent Project*****
Originally posted by nordek
I am trying to create an application for recording voice passwords and only allowing the same person to login by speaking the same word.
I have had some success but the problem is the accuracy of the program.
I am willing to pay and have little time left for completion of this project...just under 5 days actually and need to have a finished working application for demonstration then, anybody who can program this without using M/softs speech recognition as this is not accurate enough please get in touch asap.
Basically the user needs to speak one word that the computer will recognise that user by and no one else.
Help!!! I look forward to a speedy response from all the experts out there.
Nordek
this is extremely complex!
ummm... u will need people who can do OCX for voice recognition, improve it over and over again.. until it's perfect!
maybe i can do the 'art'.. if you like..
u'll need to find some people that really can do this projex..!
thx
-
Jun 5th, 2002, 09:07 AM
#3
There is no way in hell anyone could write a speech recognization app in 5 days.
-
Jun 5th, 2002, 02:58 PM
#4
Good Ol' Platypus
The best you'd be able to do (this is even pushing it) is get the waveform, and compare EVERY point. You'll also have to record some different sounds (ex. under stress, tired), so they won't have problems getting in at times.
Speech recognition is getting better, but is still VERY shifty.
All contents of the above post that aren't somebody elses are mine, not the property of some media corporation. 
(Just a heads-up)
-
Jun 16th, 2002, 12:06 AM
#5
-
Jun 16th, 2002, 09:25 PM
#6
PowerPoster
5 DAYS!!!

Good luck!
-----------------------------------------
-RJ
[email protected]
-----------------------------------------
Posting Permissions
- You may not post new threads
- You may not post replies
- You may not post attachments
- You may not edit your posts
-
Forum Rules
|
Click Here to Expand Forum to Full Width
|