speech recognition using matlab and lms algorithm

Started by ajay shah January 23, 2002

hello friends,
by using advance signal processing technique i,e LMS
algorith isolated word is to be recognised.
what r the steps for recognising this word.
to find out the coefficients shall i have to use entire
word or taking it,s segments may be due to unstationary?
thanks in advance.
ajay



hi,
how do u plan to implement it.. LS or LMS? if LMS, u
need not worry about the stationarity if the filter
order is smaller compared to the duration of
stationarity.

Quoting ajay shah <>:

> <html><body > <tt>
> <BR>
> hello friends,<BR>
> by using advance signal processing technique i,e LMS
<BR>
> algorith isolated word is to be recognised.<BR>
> what r the steps for recognising this word.<BR>
> to find out the coefficients shall i have to use
entire <BR>
> word or taking it,s segments may be due to
unstationary?<BR>
> thanks in advance.<BR>
> ajay <BR>
> <BR>
> <BR>
> </tt>
>
> <br>
>
> <!-- |**|begin egp html banner|**| -->
>
> <table border=0 cellspacing=0 cellpadding=2>
> <tr bgcolor=#FFFFCC>
> <td alignter><font size="-1"
color=#003399><b>Yahoo! Groups
> Sponsor</b></font></td>
> </tr>
> <tr bgcolor=#FFFFFF>
> <td alignter widthG0><a
>
href="http://rd.yahoo.com/M3641.1824646.3335993.1261
774/D=egroupweb/S05083376:HM/A9357/R=0/*http://sh
op.store.yahoo.com/cgi-bin/clink?
gloss2+shopping:dmad/M3641.1824646.3335993.1261774/D
=egroupweb/S05083376:HM/A9357/R=1/1011793551+http
://us.rmi.yahoo.com/rmi/http://www.gloss.com/rmi-
framed-
url/http://www.gloss.com/module/Stila/templates/whatsne
w/whatsnew_detail.jhtml%3FitemId"100038%
26mktAdTrack"800125"><img
>
src="http://us.a1.yimg.com/us.yimg.com/a/an/anchor/shop
ping/gloss/gst_ncs_beauty_winterblues.gif"
> width00 height%0 ALT="[]" border=0></a><p><hr
size=1 nowrap
> width="98%"></td>
> </tr>
> <tr><td><img alt="" width=1 height=1
> src="http://us.adserver.yahoo.com/l?
M3641.1824646.3335993.1261774/D=egroupmail/S05083
376:HM/A9357/rand0653926"></td></tr>
> </table>
>
> <!-- |**|end egp html banner|**| -- > <br>
> <tt>
> _____________________________________<BR>
> Note: If you do a simple &quot;reply&quot; with your
email client, only the
> author of this message will receive your
answer.&nbsp; You need to do a
> &quot;reply all&quot; if you want your answer to be
distributed to the
> entire group.<BR>
> <BR>
> _____________________________________<BR>
> About this discussion group:<BR>
> <BR>
> To Join:&nbsp; <BR>
> <BR>
> To Post:&nbsp; <BR>
> <BR>
> To Leave: <BR>
> <BR>
> Archives: <a
>
href="http://www.yahoogroups.com/group/matlab">http://w
ww.yahoogroups.com/group/matlab</a><BR>
> <BR>
> More DSP-Related Groups: <a
>
href="http://www.dsprelated.com/groups.php3">http://www
.dsprelated.com/groups.php3</a></tt>
> <br>
>
> <br>
> <tt>">http://docs.yahoo.com/info/terms/">Yahoo!
Terms of Service</a>.</tt>
> </br>
>
> </body></html





hi,
i am implementing on LMS
we r doing isolated spoken word recognition
we consider speech signal stationary for 20-25 msec
so we are thinking abt taking window & moving it for whole word with a step
size of half window length & finding LMS coeffi. for each window & comparing
for detection
"IS THIS APPROACH CORRECT ??? OR LMS COEFFI. OF WHOLE WORD CAN BE USED AS
PARAMETER FOR DETECTION "
thanking again
expecting for guidance
...ajay
On Wed, 23 Jan 2002 Ganesan Ramachandran wrote :
> hi,
> how do u plan to implement it.. LS or LMS? if LMS, u
> need not worry about the stationarity if the filter
> order is smaller compared to the duration of
> stationarity.
>
> Quoting ajay shah <>:
>
> > <html><body>
> >
> >
> > <tt>
> > <BR>
> > hello friends,<BR>
> > by using advance signal processing technique i,e LMS
> <BR>
> > algorith isolated word is to be recognised.<BR>
> > what r the steps for recognising this word.<BR>
> > to find out the coefficients shall i have to use
> entire <BR>
> > word or taking it,s segments may be due to
> unstationary?<BR>
> > thanks in advance.<BR>
> > ajay <BR>
> > <BR>
> > <BR>
> > </tt>
> >
> > <br>
> >
> > <!-- |**|begin egp html banner|**| -->
> >
> > <table border=0 cellspacing=0 cellpadding=2>
> > <tr bgcolor=#FFFFCC>
> > <td alignter><font size="-1"
> color=#003399><b>Yahoo! Groups
> > Sponsor</b></font></td>
> > </tr>
> > <tr bgcolor=#FFFFFF>
> > <td alignter widthG0><a
> >
> href="http://rd.yahoo.com/M3641.1824646.3335993.1261
> 774/D=egroupweb/S05083376:HM/A9357/R=0/*http://sh
> op.store.yahoo.com/cgi-bin/clink?
> gloss2+shopping:dmad/M3641.1824646.3335993.1261774/D
> =egroupweb/S05083376:HM/A9357/R=1/1011793551+http
> ://us.rmi.yahoo.com/rmi/http://www.gloss.com/rmi-
> framed-
> url/http://www.gloss.com/module/Stila/templates/whatsne
> w/whatsnew_detail.jhtml%3FitemId"100038%
> 26mktAdTrack"800125"><img
> >
> src="http://us.a1.yimg.com/us.yimg.com/a/an/anchor/shop
> ping/gloss/gst_ncs_beauty_winterblues.gif"
> > width00 height%0 ALT="[]" border=0></a><p><hr
> size=1 nowrap
> > width="98%"></td>
> > </tr>
> > <tr><td><img alt="" width=1 height=1
> > src="http://us.adserver.yahoo.com/l?
> M3641.1824646.3335993.1261774/D=egroupmail/S05083
> 376:HM/A9357/rand0653926"></td></tr>
> > </table>
> >
> > <!-- |**|end egp html banner|**| -->
> >
> >
> > <br>
> > <tt>
> > _____________________________________<BR>
> > Note: If you do a simple "reply" with your
> email client, only the
> > author of this message will receive your
> answer. You need to do a
> > "reply all" if you want your answer to be
> distributed to the
> > entire group.<BR>
> > <BR>
> > _____________________________________<BR>
> > About this discussion group:<BR>
> > <BR>
> > To Join: <BR>
> > <BR>
> > To Post: <BR>
> > <BR>
> > To Leave: <BR>
> > <BR>
> > Archives: <a
> >
> href="http://www.yahoogroups.com/group/matlab">http://w
> ww.yahoogroups.com/group/matlab</a><BR>
> > <BR>
> > More DSP-Related Groups: <a
> >
> href="http://www.dsprelated.com/groups.php3">http://www
> .dsprelated.com/groups.php3</a></tt>
> > <br>
> >
> > <br>
> > <tt>">http://docs.yahoo.com/info/terms/">Yahoo!
> Terms of Service</a>.</tt>
> > </br>
> >
> > </body></html>
> >
> > ------------------------ Yahoo! Groups Sponsor
>
> _____________________________________
> Note: If you do a simple "reply" with your email client,
> only the author of this message will receive your
> answer. You need to do a "reply all" if you want your
> answer to be distributed to the entire group.
>
> _____________________________________
> About this discussion group:
>
> To Join:
>
> To Post:
>
> To Leave:
>
> Archives: http://www.yahoogroups.com/group/matlab
>
> More DSP-Related Groups: http://www.dsprelated.com/group-
> s.php3
>
> ">http://docs.yahoo.com/info/terms/




hello,
i am planning to calculate by off line i.e. taking speech from wav files.

initial filter coefficient r set w=0;
and all new coefficients are updated by
Wi+1=Wi + 2*mu*e*u;
u i/p array
e-instantanious error.
next successive window we use previous as initial coeff.
but the error is not converging
window size is 23.2 msec was taken & step size was 23.2/25
if i try to move window continuosly to avoid sudden change of statestical char.
it takes too much time
error gives same shape as of i/p
what is solution.????
...ajay On Thu, 24 Jan 2002 Ganesan Ramachandran wrote :
> hi,
> how do u plan to calculate the coefficients? thro
> online/batch - LMS gradient descent? in that case, u'll
> be dealing only with samples of length of the filder
> order
> ----- Original Message -----
> From: ajay shah
> To: Ganesan Ramachandran
> Cc:
> Sent: Thursday, January 24, 2002 8:29 AM
> Subject: Re: Re: [matlab] speech recognition using
> matlab and lms algorithm >
> hi,
> i am implementing on LMS
> we r doing isolated spoken word recognition
> we consider speech signal stationary for 20-25 msec
> so we are thinking abt taking window & moving it for
> whole word with a step size of half window length &
> finding LMS coeffi. for each window & comparing for
> detection
> "IS THIS APPROACH CORRECT ??? OR LMS COEFFI. OF
> WHOLE WORD CAN BE USED AS PARAMETER FOR DETECTION "
> thanking again
> expecting for guidance
> ...ajay >
> On Wed, 23 Jan 2002 Ganesan Ramachandran wrote :
> > hi,
> > how do u plan to implement it.. LS or LMS? if LMS,
> u
> > need not worry about the stationarity if the filter
> > order is smaller compared to the duration of
> > stationarity.
> >
> > Quoting ajay shah <>:
> >
> > > <html><body>
> > >
> > >
> > > <tt>
> > > <BR>
> > > hello friends,<BR>
> > > by using advance signal processing technique i,e
> LMS
> > <BR>
> > > algorith isolated word is to be recognised.<BR>
> > > what r the steps for recognising this word.<BR>
> > > to find out the coefficients shall i have to use
> > entire <BR>
> > > word or taking it,s segments may be due to
> > unstationary?<BR>
> > > thanks in advance.<BR>
> > > ajay <BR>
> > > <BR>
> > > <BR>
> > > </tt>
> > >
> > > <br>
> > >
> > > <!-- |**|begin egp html banner|**| -->
> > >
> > > <table border=0 cellspacing=0 cellpadding=2>
> > > <tr bgcolor=#FFFFCC>
> > > <td alignter><font size="-1"
> > color=#003399><b>Yahoo! Groups
> > > Sponsor</b></font></td>
> > > </tr>
> > > <tr bgcolor=#FFFFFF>
> > > <td alignter widthG0><a
> > >
> > href="http://rd.yahoo.com/M3641.1824646.3335993.1-
> 261
> > 774/D=egroupweb/S05083376:HM/A9357/R=0/*http:/-
> /sh
> > op.store.yahoo.com/cgi-bin/clink?
> > gloss2+shopping:dmad/M3641.1824646.3335993.126177-
> 4/D
> > =egroupweb/S05083376:HM/A9357/R=1/1011793551+h-
> ttp
> > ://us.rmi.yahoo.com/rmi/http://www.gloss.com/rmi-
> > framed-
> > url/http://www.gloss.com/module/Stila/templates/what-
> sne
> > w/whatsnew_detail.jhtml%3FitemId"100038%
> > 26mktAdTrack"800125"><img
> > >
> > src="http://us.a1.yimg.com/us.yimg.com/a/an/anchor/s-
> hop
> > ping/gloss/gst_ncs_beauty_winterblues.gif"
> > > width00 height%0 ALT="[]" border=0></a><p><hr
> > size=1 nowrap
> > > width="98%"></td>
> > > </tr>
> > > <tr><td><img alt="" width=1 height=1
> > > src="http://us.adserver.yahoo.com/l?
> > M3641.1824646.3335993.1261774/D=egroupmail/S05-
> 083
> > 376:HM/A9357/rand0653926"></td></tr>
> > > </table>
> > >
> > > <!-- |**|end egp html banner|**| -->
> > >
> > >
> > > <br>
> > > <tt>
> > > _____________________________________<BR>
> > > Note: If you do a simple "reply" with your
> > email client, only the
> > > author of this message will receive your
> > answer. You need to do a
> > > "reply all" if you want your answer to be
> > distributed to the
> > > entire group.<BR>
> > > <BR>
> > > _____________________________________<BR>
> > > About this discussion group:<BR>
> > > <BR>
> > > To Join: <BR>
> > > <BR>
> > > To Post: <BR>
> > > <BR>
> > > To Leave: <BR>
> > > <BR>
> > > Archives: <a
> > >
> > href="http://www.yahoogroups.com/group/matlab">http:-
> //w
> > ww.yahoogroups.com/group/matlab</a><BR>
> > > <BR>
> > > More DSP-Related Groups: <a
> > >
> > href="http://www.dsprelated.com/groups.php3">http://-
> www
> > .dsprelated.com/groups.php3</a></tt>
> > > <br>
> > >
> > > <br>
> > > <tt>">http://docs.yahoo.com/info/terms/">Yahoo!
> > Terms of Service</a>.</tt>
> > > </br>
> > >
> > > </body></html>
> > >
> > >
> >
> >
> > ------------------------ Yahoo! Groups Sponsor
> >
> > _____________________________________
> > Note: If you do a simple "reply" with your email
> client,
> > only the author of this message will receive your
> > answer. You need to do a "reply all" if you want
> your
> > answer to be distributed to the entire group.
> >
> > _____________________________________
> > About this discussion group:
> >
> > To Join:
> >
> > To Post:
> >
> > To Leave:
> >
> > Archives: http://www.yahoogroups.com/group/matlab
> >
> > More DSP-Related Groups:
> http://www.dsprelated.com/group-
> > s.php3
> >
> > ">http://docs.yahoo.com/info/terms/
> >
> >
>
> _____________________________________
> Note: If you do a simple "reply" with your email
> client, only the author of this message will receive
> your answer. You need to do a "reply all" if you want
> your answer to be distributed to the entire group.
>
> _____________________________________
> About this discussion group:
>
> To Join:
>
> To Post:
>
> To Leave:
>
> Archives: http://www.yahoogroups.com/group/matlab
>
> More DSP-Related Groups: http://www.dsprelated.com/gro-
> ups.php3 >




hi,
i think u misunderstood what i meant by online LMS..
i apologize for not being clear... i guess u haven't
had a formal introduction to gradient descent and
LMS.. if u know them please skip the lines between C
language comments (/* & */)

/* gradient descent
the adaptive algorithms such as LMS, RLS & their
variants belong to a category called gradient descent
algorithms. the filtering operation done by this
adaptive filter can be considered as trying to
approximate a function in the multidimensional signal
space spanned using the delayed versions of the input
signal as the co-ordinate axes. if the filtering is
done in a linear fashion (i.e., with an FIR), then the
error between the desired and the output of the system
has a parabolic shape in the space spanned by the co-
efficients of the filter (i.e., weights) . so, to
travel down the parabola and to reach the minimum
error, we use the information from the gradient on the
parabolic surface. that's y these are known as
gradient descent algorithms. if u have trouble
understanding this, i suggest that u read any standard
adaptive filtering books like simon haykin or
principe.

LMS

in LMS there are two ways to do it. 1. online , 2.
batch.. the difference is whether u want to update the
weights instantaneous error (the e in ur equation) or
u want to update with an error averaged over some
samples. let me explain the online mode as it is
easier to implement and understand.

in online LMS, what u basically do is say if u have
a filter order N, then u take N samples from the input
signal, pass it thro an FIR, find the error between
output and the desired and then use the error to
update the weights of the FIR... then replace the
filter input with the input signal values one by one
and proceed. since u handle with only N samples at a
time, u don't have to worry about the stationarity of
the signal and all as N is much smaller compared to
the duration of stationarity.
*/

if u feel it goes way above the head, i strongly
suggest that u take a look at a standard book on
adaptive DSP.. if u need any clarifications, feel free
to contact me.
hope this helps.
Ganesan.

hello,
i am planning to calculate by off line i.e. taking
speech from wav files.

initial filter coefficient r set w=0;
and all new coefficients are updated by
Wi+1=Wi + 2*mu*e*u;
u i/p array
e-instantanious error.
next successive window we use previous as initial
coeff.
but the error is not converging
window size is 23.2 msec was taken & step size was
23.2/25
if i try to move window continuosly to avoid sudden
change of statestical char. it takes too much time
error gives same shape as of i/p
what is solution.????
...ajay On Thu, 24 Jan 2002 Ganesan Ramachandran wrote :
> hi,
> how do u plan to calculate the coefficients? thro
> online/batch - LMS gradient descent? in that case,
u'll
> be dealing only with samples of length of the filder
> order





hi
i have gone through simon haykin and lim , oppenham books on adaptive filtering
before starting
the problem is not in cal. coefficient but which coeff should be used for
speech recognition
we can't use only last coeff for differentiation
so which coeff should be used
as signal is nonlinear coeff changes till last the coeff. gets settle for some
time & then as statistic property changes coeff change as expected
so we r not getting which coeff should be used
or we have to use coeff after successive intervals & then use dynamic time
warping for comparing
thanks in advance
...........ajay

On Fri, 25 Jan 2002 Ganesan Ramachandran wrote :
> hi,
> i think u misunderstood what i meant by online LMS..
> i apologize for not being clear... i guess u haven't
> had a formal introduction to gradient descent and
> LMS.. if u know them please skip the lines between C
> language comments (/* & */)
>
> /* gradient descent
> the adaptive algorithms such as LMS, RLS & their
> variants belong to a category called gradient descent
> algorithms. the filtering operation done by this
> adaptive filter can be considered as trying to
> approximate a function in the multidimensional signal
> space spanned using the delayed versions of the input
> signal as the co-ordinate axes. if the filtering is
> done in a linear fashion (i.e., with an FIR), then the
> error between the desired and the output of the system
> has a parabolic shape in the space spanned by the co-
> efficients of the filter (i.e., weights) . so, to
> travel down the parabola and to reach the minimum
> error, we use the information from the gradient on the
> parabolic surface. that's y these are known as
> gradient descent algorithms. if u have trouble
> understanding this, i suggest that u read any standard
> adaptive filtering books like simon haykin or
> principe.
>
> LMS
>
> in LMS there are two ways to do it. 1. online , 2.
> batch.. the difference is whether u want to update the
> weights instantaneous error (the e in ur equation) or
> u want to update with an error averaged over some
> samples. let me explain the online mode as it is
> easier to implement and understand.
>
> in online LMS, what u basically do is say if u have
> a filter order N, then u take N samples from the input
> signal, pass it thro an FIR, find the error between
> output and the desired and then use the error to
> update the weights of the FIR... then replace the
> filter input with the input signal values one by one
> and proceed. since u handle with only N samples at a
> time, u don't have to worry about the stationarity of
> the signal and all as N is much smaller compared to
> the duration of stationarity.
> */
>
> if u feel it goes way above the head, i strongly
> suggest that u take a look at a standard book on
> adaptive DSP.. if u need any clarifications, feel free
> to contact me.
> hope this helps.
> Ganesan.
>
> hello,
> i am planning to calculate by off line i.e. taking
> speech from wav files.
>
> initial filter coefficient r set w=0;
> and all new coefficients are updated by
> Wi+1=Wi + 2*mu*e*u;
> u i/p array
> e-instantanious error.
> next successive window we use previous as initial
> coeff.
> but the error is not converging
> window size is 23.2 msec was taken & step size was
> 23.2/25
> if i try to move window continuosly to avoid sudden
> change of statestical char. it takes too much time
> error gives same shape as of i/p
> what is solution.????
> ...ajay > On Thu, 24 Jan 2002 Ganesan Ramachandran wrote :
> > hi,
> > how do u plan to calculate the coefficients? thro
> > online/batch - LMS gradient descent? in that case,
> u'll
> > be dealing only with samples of length of the filder
> > order > ------------------------ Yahoo! Groups Sponsor
>
> _____________________________________
> Note: If you do a simple "reply" with your email client,
> only the author of this message will receive your
> answer. You need to do a "reply all" if you want your
> answer to be distributed to the entire group.
>
> _____________________________________
> About this discussion group:
>
> To Join:
>
> To Post:
>
> To Leave:
>
> Archives: http://www.yahoogroups.com/group/matlab
>
> More DSP-Related Groups: http://www.dsprelated.com/group-
> s.php3
>
> ">http://docs.yahoo.com/info/terms/