Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.
I wish you best of luck, Junus.
The speech recognition runs on a beagleboard (Embedded Linux) running some toolkit called HTK.
The movement and head motion are based on Atmel AVR Atmega32 microcontroller.
I think PLC is not the good choice for robots like this.
- - - Updated - - -
How much...
Me and four of my friends have developed a robot waitress that serves the customers of restaurants and hotels; it understands
Arabic speech (continuous speech) and interacts with the customers and the kitchen-man by listening to
their orders. It moves around the place, chatting with the...
snr
You should transmit the "Same" X many times.
You receive different Y's.
The Y's average is the X you are transmitting in case you transmitting so many times.
Added after 1 minutes:
As you see, you don't have to know X, but this X should be transmitted many times.
snr
Y(t)=X(t)+R.V~(mean=0,known variance)
You can use the info that noise is a RV that has a zero mean and is Wide Sense Stationary.
So, I think, when you can transmit the same signal X many times and monitor the o/p Y's.
The average of Y's is a good estimation of X, assuming you transmitted X...
I have done a MATLAB code for Voice Recognition Algorithm, It's about 200 lines of calculations and memry accessing.
I want to convert this project into hardware project that works in real-time.
The problem is that the code has a lot of complex calculations and frequency domain analysis.
What's...
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.