View previous topic :: View next topic |
Author |
Message |
benoit
Joined: 24 Jul 2007 Posts: 177
|
Posted: Sat Oct 19, 2019 10:39 am Post subject: voice recognition system and voice basic programing with han |
|
|
hello i am a little ennoyed that windows as voice recognition system and not bascom yet
is it a way to create an interface with the actual basic bascom to create a table of small voice recognition with windows and transalate to avr basic for permit the avr to have voice command for fun later ?
(BASCOM-AVR version : 2.0.7.3 , Latest : 2.0.8.2 ) |
|
Back to top |
|
|
MWS
Joined: 22 Aug 2009 Posts: 2262
|
Posted: Sat Oct 19, 2019 1:03 pm Post subject: Re: voice recognition system and voice basic programing with |
|
|
benoit wrote: | hello i am a little ennoyed that windows as voice recognition system and not bascom yet |
If anything, you're annoyed.
I can be annoyed too if it rains, whilst I want the sun to shine, but guess what: my anger hasn't any effect on the weather.
Quote: | is it a way to create an interface with the actual basic bascom to create a table of small voice recognition with windows and transalate to avr basic for permit the avr to have voice command for fun later ? |
No.
Simply imagine the up to 16 MIPS an ATMega can do, combined with some kilos of SRam compared to Megatons of PC memory and 336.000 MIPS of an Intel i7-5960X (source Wiki).
Does this make the difference? Yes, it does. |
|
Back to top |
|
|
Duval JP
Joined: 22 Jun 2004 Posts: 1161 Location: France
|
Posted: Sun Oct 20, 2019 4:28 pm Post subject: |
|
|
error of message _________________ pleasure to learn, to teach, to create
Last edited by Duval JP on Sun Oct 20, 2019 5:24 pm; edited 1 time in total |
|
Back to top |
|
|
EDC
Joined: 26 Mar 2014 Posts: 971
|
Posted: Sun Oct 20, 2019 4:48 pm Post subject: |
|
|
I was make simple voice recognition system in Bascom in 2015. This project win Bascom contest in Poland
..but that Atmega32 was my first processor so no much SRAM(2KB) i have then... Now maybe some 644P(4KB) or even 1284P(16KB SRAM) will be more suitable.
You can see project site here https://bart-projects.cba.pl/mika.html with complete code and one old video (sorry for the quality - I dont have phone with HD camera yet ) |
|
Back to top |
|
|
JC
Joined: 15 Dec 2007 Posts: 585 Location: Cleveland, OH
|
Posted: Sun Oct 20, 2019 5:41 pm Post subject: |
|
|
Surely it depends upon your goal.
As noted above, for a large vocabulary, and speaker independent system, perhaps with background noise to content with, one needs the power of a PC.
If your goals are more modest, say one speaker, (not anybody), with a limited vocabulary, (say 10 known words, not an unlimited vocabulary), and a good analog front end signal, with minimal background noise, then one could certainly write a simple voice recognition system.
One doesn't need to do real time, sliding data window, DFTs to process the data.
One can look for silence, the start and end of words, the duration of words, the number of zero crossings during different parts of the word, (e.g. first 20% of the word, 2nd, 20% of the word, etc.), the relative amplitude of the different parts of the word, etc.
One can process the above info very easily, and build a table of parameters, (the above characteristics), that define the word.
One then processes the real time input signal, measures its parameters, and sees if it is a close enough match to the table of known words.
That, however, is a far cry from speaker independent, unlimited vocabulary, voice recognition, (speech to text, speech to command, etc.).
JC |
|
Back to top |
|
|
|
|
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum You cannot attach files in this forum You cannot download files in this forum
|
|