Peter wrote:
> Vitaliy <piclist <at> maksimov.org> writes:
>> Found it:
>>
>> http://www.circuitcellar.com/pastissues/articles/Stewart91/text.htm
>
> Nice find Vitalyi. I was thinking more along the lines of using an audio
> spectrum analyzer chip's outputs as cepstral inputs to a pic. I will look 
> into
> your link when I have time.

The project is based on a different theory than IBM's shoebox (I realized 
after rereading the article). In fact, the author specifically says:

==
A note of caution: when using Tiny Voice, don't use a lot of short words 
(e.g., the numbers "one", "two", etc.). They're a bit beyond its 
capabilities.
==

IBM's algorithm is based on a linguistic accident, while Tiny Voice is a 
more general purpose solution, but with its own set of limitations.

Vitaliy 

-- 
http://www.piclist.com PIC/SX FAQ & list archive
View/change your membership options at
http://mailman.mit.edu/mailman/listinfo/piclist