tag:blogger.com,1999:blog-5674879503126200888.post7444094884847620627..comments2023-10-22T06:30:57.331-07:00Comments on <a href="https://www.husseinnasser.com/p/about-hussein.html">Hussein Nasser</a>: Speech Recognition: Why everybody is heading north?Hussein Nasserhttp://www.blogger.com/profile/18310476423554125845noreply@blogger.comBlogger5125tag:blogger.com,1999:blog-5674879503126200888.post-73770623985821861902009-03-26T03:30:00.000-07:002009-03-26T03:30:00.000-07:00You are always welcome and I'm always happy to mak...You are always welcome and I'm always happy to make a contribution to your already brilliant ideas. ;)PragmaTechiehttps://www.blogger.com/profile/10555106847946822242noreply@blogger.comtag:blogger.com,1999:blog-5674879503126200888.post-20739469169269732622009-03-25T23:11:00.000-07:002009-03-25T23:11:00.000-07:00@Cody!!"That would not have been a problem except ...@Cody!!<BR/><BR/>"That would not have been a problem except that <BR/>it remembers signals and not meanings of words."<BR/><BR/>Great analysis!<BR/>to invent another signal that carry the meaning of the word<BR/><BR/>I guess our brain is reading the signal of the meaning to understand the content and then reading the signal of the actual sound for emotion purposes.. (strong voice, girly voice, sexy voice etc..) <BR/><BR/>or vise versa (read the voice signal then the meaning signal)<BR/><BR/>However how this is done need some research..<BR/><BR/><BR/>I loved your post and differentially it could lead the readers to a promising stage..<BR/><BR/><BR/>Lets just put anything you are thinking of you don't have to be a computer guy, an IT guy or even a speech recognition expert..<BR/><BR/><BR/>thanks again Cody !Hussein Nasserhttps://www.blogger.com/profile/18310476423554125845noreply@blogger.comtag:blogger.com,1999:blog-5674879503126200888.post-69187596424044853572009-03-25T18:51:00.000-07:002009-03-25T18:51:00.000-07:00Instead of North, they should be traveling East in...Instead of North, they should be traveling East in search of light in programming. :)<BR/><BR/>Seriously, the problem with speech recognition, and with OCR, as Yassen points out, is the computer's accuracy with details. Yup, its strength, accuracy, is also its weakness in this case.<BR/><BR/>It's so accurate that it can sense a slight variation in audio signal between Roy's voice sample of the word petrified and that of yours.<BR/><BR/>That would not have been a problem except that it remembers signals and not meanings of words. So, even if there is no variation in meaning (same word) but there is a variation in signal (as the same word is spoken by different persons), it considers it a different word.<BR/><BR/>Part of the solution to this might be to teach the computer some signal (audio or visual) abstraction.<BR/><BR/>It should learn what details, and to what extent those details, of a data can change and still <I>be</I> the same data. Example, a dog can change color and height and still be a dog.PragmaTechiehttps://www.blogger.com/profile/10555106847946822242noreply@blogger.comtag:blogger.com,1999:blog-5674879503126200888.post-91565880684056301822009-03-24T07:29:00.000-07:002009-03-24T07:29:00.000-07:00@Yaseen,That's the same story you are right.Its go...@Yaseen,<BR/><BR/>That's the same story you are right.<BR/><BR/>Its good to bring the ideas to fresh air, maybe someone will read this blog one day and decide to take the lead.Hussein Nasserhttps://www.blogger.com/profile/18310476423554125845noreply@blogger.comtag:blogger.com,1999:blog-5674879503126200888.post-71292508008212661852009-03-24T07:16:00.000-07:002009-03-24T07:16:00.000-07:00Speaking of that, I also find the current OCR tech...Speaking of that, I also find the current OCR technology lacking, each library I've tried can recognize full images included with it, but when I provide a clear black text on white background sample the results are garbage.<BR/><BR/>Someone should find a new way to do OCR instead of the old techniques.Yaseen titihttps://www.blogger.com/profile/13465786576169645016noreply@blogger.com