Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news.harvard.edu!news2.near.net!MathWorks.Com!usenet.eel.ufl.edu!gmi!news1.oakland.edu!rcsuna.gmr.com!kocrsv01!news
From: ddturner@kocrsv01.delcoelect.com
Subject: Re: wavelets and NN 
Content-Type: TEXT/PLAIN; charset=US-ASCII
Message-ID: <1994Sep15.211834.21752@kocrsv01.delcoelect.com>
Sender: news@kocrsv01.delcoelect.com (Usenet News Account)
Nntp-Posting-Host: koadpc20
Organization: Delco Electronics Corp.
X-Newsreader: NEWTNews & Chameleon -- TCP/IP for MS Windows from NetManage
References: <35987j$r4n@kodak.rdcs.Kodak.COM>
     
Mime-Version: 1.0
Date: Thu, 15 Sep 1994 23:16:01 GMT
Lines: 42


In article <35987j$r4n@kodak.rdcs.Kodak.COM>, <martin@belteshazzar.Kodak.COM> 
writes:
> 
> -- 
> I am currently working on a thesis project in speech recognition that
> uses wavelet tranforms to generate the feature vector and then training
> some of the vectors into associative memory (NN).  I have recorded
> 15 people saying the vowels from the Peterson/Barney group to use as
						^^^^^^
Is this the big purple dinosaur??? :-)

Sorry couldn't resist.

> my sound data base.  Some of these are trained into the associative
> memory and some are presented to the network for recognition.
>  
> My problem is that I cannot seem to generate good, distinct, feature
> vectors using the wavelet (DAUB4 as shown in numerical recipes).  My
> approach has been to parse the vowel from the beginning of each sound
> into a 1024 byte buffer, normalize the data, feed it into the wavelet
> algorithm, and then add up the coefficients in each section of the
> resulting wavelet transform (first 2, second 2, next 4, next 8...etc).
> There is some similarity in the summed coefficients for a given sound
> spoken by different people, but not enough to give me distinct feature
> vectors for a given sound.
>  
> I have tried the higher order wavelet transforms from the nr book with
> no improvement.
>  
> Is there anyone out there that can tell me what I am doing wrong?????
> It is probably a lack of understanding on my part as to how to interpret
> the wavelet transform.
>  
> Thanks in advance.......
> -- 
> Craig W. Martin                            martin@belteshazzar.Kodak.COM

Doug Turner
Adv. Vehicle Systems
Delco Electronics
ddturner@kocrsv01.delcoelect.com
