IPB

Welcome Guest ( Log In | Register )

 
Reply to this topicStart new topic
Voice Matching Software for Security Solution, Using Speech codecs to match Voice.
TechnoMania
post Sep 25 2004, 13:04
Post #1





Group: Members
Posts: 57
Joined: 8-August 04
From: India
Member No.: 16106



Hi All,

I dunno is such a kind of a software exists or is possible thru programming.

CODE
All i want is  
~~~~~~~
The is a voice file present on a Computer which was recorded earlier by the person (suppose he has recorded his voice as "hi i am xyz").

Now i have to verify that the voice is his only so he will talk the same thing which
was recorded earlier i.e. "hi i am xyz" if the 2 voice match the software will
tell me that the 2 voice match exactly.

the frequecy peaks will be matched to check the voice i suppose or something like that.


Is there such a type of software in existance or it exists only in movies.

If yes whats the name of the software and what all things will be required to
configure the software on my pc.

If such a thing does not exist just leave it i just wanted to know about it.
Go to the top of the page
+Quote Post
mr_projects
post Jul 19 2005, 22:36
Post #2





Group: Members
Posts: 6
Joined: 19-July 05
Member No.: 23420



im looking for the same thing !

i think its "voice pattern matching" technology , did you find anything ?
thanks
Go to the top of the page
+Quote Post
jobh
post Jul 19 2005, 23:17
Post #3





Group: Members
Posts: 3
Joined: 23-February 05
Member No.: 20095



"automatic speaker recognition" is also a good search term.

Software exists, sure, but it is not very reliable. It's still an active research area.
Go to the top of the page
+Quote Post
HotshotGG
post Jul 19 2005, 23:33
Post #4





Group: Members
Posts: 1593
Joined: 24-March 02
From: Revere, MA
Member No.: 1607



QUOTE
Software exists, sure, but it is not very reliable. It's still an active research area.


Yes, it's an definitely an interesting area of research to study. Most speech recognition systems are based upon Hidden Markov Models which are statistical models. ASR is a form of dictation. biggrin.gif. Look up "grammar constrained recogniton" and "natural language recognition". What I can gather from reading a little those are the two most common types, each one has there obvious advantages and disadvantages.

This post has been edited by HotshotGG: Jul 19 2005, 23:53


--------------------
College student/IT Assistant
Go to the top of the page
+Quote Post
mr_projects
post Jul 20 2005, 12:02
Post #5





Group: Members
Posts: 6
Joined: 19-July 05
Member No.: 23420



thanks guys that was really helpful

does anyone have names of these software/links ?
Go to the top of the page
+Quote Post
jobh
post Jul 20 2005, 16:10
Post #6





Group: Members
Posts: 3
Joined: 23-February 05
Member No.: 20095



QUOTE (mr_projects @ Jul 20 2005, 01:02 PM)
does anyone have names of these software/links ?
*


Random examples: SpeechSecure (commercial) or PUMS (research). I'm sure you'll find others through google.
Go to the top of the page
+Quote Post

Reply to this topicStart new topic
1 User(s) are reading this topic (1 Guests and 0 Anonymous Users)
0 Members:

 



RSS Lo-Fi Version Time is now: 20th April 2014 - 23:06