Speech Recognition using Butterworth filters

I am aiming to build a very basic speech recognition system around an
8-bit microcontroller(PIC / AVR), which is capable of 'recognizing'
four to eight words..(i.e, give a specific string output when it
receives the corresponding input data through a mic.)

Someone told me that designing Butterworth filters for processing the
input data and then sampling it at different points is a pretty good
strategy.... However, all I can find on the Net regarding this is a
lot of highly obfuscated jargon....So, could anyone please direct me
to a good, clear source explaining this (or any other) speech
recogntion algorithm in minute detail?.....

Hope you people can throw some light on this............

Thanks...

Mandar Gokhale wrote:

> I am aiming to build a very basic speech recognition system around an
> 8-bit microcontroller(PIC / AVR), which is capable of 'recognizing'
> four to eight words..(i.e, give a specific string output when it
> receives the corresponding input data through a mic.)
> 
> Someone told me that designing Butterworth filters for processing the
> input data and then sampling it at different points is a pretty good
> strategy.... However, all I can find on the Net regarding this is a
> lot of highly obfuscated jargon....So, could anyone please direct me
> to a good, clear source explaining this (or any other) speech
> recogntion algorithm in minute detail?.....
> 
> Hope you people can throw some light on this............

1. It is indeed possible to make a very basic word matching engine with 
PIC or AVR.

2. It is also obvious that you don't have enough guts to accomplish that.

So, if you really need to get something to work, use a chip from 
Sensory. If this is just an idle interest,  better GFY.


VLV

Vladimir Vassilevsky <antispam_bogus@hotmail.com> writes:

> better GFY.

Vlad, does that mean what I think it means? That's really, really
rude, and no matter how much the OP might "deserve" such a sentiment,
it really just serves to bring the spirit of the group to a new low.

How about setting your sites on higher ground?
-- 
%  Randy Yates                  % "Ticket to the moon, flight leaves here today 
%% Fuquay-Varina, NC            %  from Satellite 2"
%%% 919-577-9882                % 'Ticket To The Moon' 
%%%% <yates@ieee.org>           % *Time*, Electric Light Orchestra
http://www.digitalsignallabs.com

Mandar Gokhale wrote:
> I am aiming to build a very basic speech recognition system around an
> 8-bit microcontroller(PIC / AVR), which is capable of 'recognizing'
> four to eight words..(i.e, give a specific string output when it
> receives the corresponding input data through a mic.)
> 
> Someone told me that designing Butterworth filters for processing the
> input data and then sampling it at different points is a pretty good
> strategy.... However, all I can find on the Net regarding this is a
> lot of highly obfuscated jargon....So, could anyone please direct me
> to a good, clear source explaining this (or any other) speech
> recogntion algorithm in minute detail?.....
> 
> Hope you people can throw some light on this............
> 
> Thanks...

You are tackling a much more complex project than you may realize.
I suggest you ask on comp.speech.research . There people there willing 
and qualified to point you to appropriate introductory material - they 
like to get people interested in their field. Polite but naive questions 
are courteously answered.

A question though. Do you really need something that would be recognized 
as "speech recognition"? Do you need to recognize words or perhaps 
sounds that can be produced by a voice?

On Dec 28, 5:38 am, Mandar Gokhale <stallo...@gmail.com> wrote:
> I am aiming to build a very basic speech recognition system around an
> 8-bit microcontroller(PIC / AVR), which is capable of 'recognizing'
> four to eight words..(i.e, give a specific string output when it
> receives the corresponding input data through a mic.)
>
> Someone told me that designing Butterworth filters for processing the
> input data and then sampling it at different points is a pretty good
> strategy.... However, all I can find on the Net regarding this is a
> lot of highly obfuscated jargon....So, could anyone please direct me
> to a good, clear source explaining this (or any other) speech
> recogntion algorithm in minute detail?.....
>
> Hope you people can throw some light on this............
>
> Thanks...

I would use cross-correlation myself if the processor was fast enough.
The trouble with using filters on their own will be that it response
to bullshit commands with one on your list.

Hardy

On Dec 27, 12:19 pm, Randy Yates <ya...@ieee.org> wrote:
> Vladimir Vassilevsky <antispam_bo...@hotmail.com> writes:
> > better GFY.
>
> Vlad, does that mean what I think it means? That's really, really
> rude, and no matter how much the OP might "deserve" such a sentiment,
> it really just serves to bring the spirit of the group to a new low.
>
> How about setting your sites on higher ground?

it's funny, but they kicked me outa Wikipedia (specifically banned me
from editing from my account User:rbj) because of rude or disruptive
or some excuse like that.  but i never said GFY to anyone.

fortunately, at these unmoderated USENET groups, there ain't no admins
that can block you.

unfortunately, at these unmoderated USENET groups, there ain't no
admins that can block the spam bastards.

r b-j

robert bristow-johnson wrote:

> it's funny, but they kicked me outa Wikipedia (specifically banned me
> from editing from my account User:rbj)

And you are still sad because of that nonsense?

> because of rude or disruptive
> or some excuse like that.

IIRC it had something to do with gays and/or evolutionists, right?

>  but i never said GFY to anyone.

You should. It is such a pleasure to call things with their right names.

> 
> fortunately, at these unmoderated USENET groups, there ain't no admins
> that can block you.
> 
> unfortunately, at these unmoderated USENET groups, there ain't no
> admins that can block the spam bastards.

Here is a short OT moralistic story:

A man comes to psychoanalyst �onsultant:

- Hello doctor. I have a problem: nobody likes me. Nobody makes friends 
with me. �an you help me, you ugly fat senile old man?


VLV

robert bristow-johnson <rbj@audioimagination.com> writes:

> On Dec 27, 12:19 pm, Randy Yates <ya...@ieee.org> wrote:
>> Vladimir Vassilevsky <antispam_bo...@hotmail.com> writes:
>> > better GFY.
>>
>> Vlad, does that mean what I think it means? That's really, really
>> rude, and no matter how much the OP might "deserve" such a sentiment,
>> it really just serves to bring the spirit of the group to a new low.
>>
>> How about setting your sites on higher ground?
>
> it's funny, but they kicked me outa Wikipedia (specifically banned me
> from editing from my account User:rbj) because of rude or disruptive
> or some excuse like that.  but i never said GFY to anyone.
>
> fortunately, at these unmoderated USENET groups, there ain't no admins
> that can block you.

Yeah, that's the situation here. Vlad made a statement, and I did too.

I suspect that the types of things you were kicked out of Wikipedia for
were far from a blatant GFY.
-- 
%  Randy Yates                  % "Remember the good old 1980's, when 
%% Fuquay-Varina, NC            %  things were so uncomplicated?"
%%% 919-577-9882                % 'Ticket To The Moon' 
%%%% <yates@ieee.org>           % *Time*, Electric Light Orchestra
http://www.digitalsignallabs.com

On 28 Des, 02:20, robert bristow-johnson <r...@audioimagination.com>
wrote:

> it's funny, but they kicked me outa Wikipedia (specifically banned me
> from editing from my account User:rbj) because of rude or disruptive
> or some excuse like that. &#4294967295;

Would that by any chance have been caused by any statement of
yours regarding the sampling theorem or Dirac's Delta function?

> but i never said GFY to anyone.

As far as I am concerned, the important line is drawn between
attacking the argument and attacking the person making the argument.
My experience is that if one argumes based on very basic premises
the oponent interprets this as a direct comment on his or her
(in)competence: "so you think I, who have umpteen years of
experience, don't understand *such* a simple premise?"

Unfortunately, more often than not, the net effect on the
discussion is much the same as would be caused by a blunt
statement like "GFY", though. Even if that is never my
intenetion.

Rune

Rune Allnor wrote:


> As far as I am concerned, the important line is drawn between
> attacking the argument and attacking the person making the argument.

Dr. Rune, you got it all vise versa. The whole purpose of attacking the 
argument is proving technically that the person making this argument is 
the idiot. The more logical you are, the more damage you are making to 
your opponent.
:)

> My experience is that if one argumes based on very basic premises
> the oponent interprets this as a direct comment on his or her
> (in)competence: "so you think I, who have umpteen years of
> experience, don't understand *such* a simple premise?"

You can count this comment as a point to you :)

> Unfortunately, more often than not, the net effect on the
> discussion is much the same as would be caused by a blunt
> statement like "GFY", though.

 From the two debaters, one is always the idiot, and the other one is 
the scoundrel :)

> Even if that is never my
> intenetion.

Of course. You always have only the good wishes :)

> 
> Rune

It is pleasure to see you again.

VLV