Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!samsung!rex!uflorida!mlb.semi.harris.com!trantor.harris-atd.com!x102a!mlaprade
From: mlaprade@x102a.harris-atd.com (laprade maria 42641)
Newsgroups: comp.dsp
Subject: speech + noise
Message-ID: <6003@trantor.harris-atd.com>
Date: 5 Apr 91 13:47:28 GMT
Sender: news@trantor.harris-atd.com
Reply-To: mlaprade@x102a.ess.harris.com (laprade maria 42641)
Distribution: all
Organization: Harris Corporation GSS, Melbourne, Florida
Lines: 26

I have a clean speaker database where I use the following to extract
features:
use energy and zero crossing to find voiced speech,
pre-emphasize and high pass filter,
autocorrelate.

I was satisfied with those results and decided to add noise. I added
white noise and processed it exactly the same way. For most of the speakers
I have lost about half the number of features extracted ( I think I'm
losing them because the pitch is calculated as a too high frequency. I
do know that the zero crossing value has now doubled, and the energy 
threshold has increased about 100x for a SNR of 10dB.) Which I thought was
reasonable. However I am left with less than 10 samples for 1 particular
speaker. 

My question is am I incorrect to add in white noise, or do I need to
modify my processing equations. I'm neither a speech nor a signal
processing type engineer, I just need a database to feed to my neural 
network so please be explicit with your help. Thanks.



-- 
Maria Laprade			ARPA: mlaprade@x102a.harris-atd.com
Harris Corporation - GASD	UUCP: ...uunet!x102a!mlaprade
Palm Bay, Florida		voice: (407)727-4920