Hi singh,
there are "methods":
- aquire the sound signal
- do some mathematical analysis (like FFT...)
- compare the result with your database of the supported commands...
Maybe you should ask engineers working for Apple or Samsung to tell you how they made Siri or S-Voice. Atleast Apple uses some hardware that supports the mathematical analysis step...
Best regards,
GerdW
CLAD, using 2009SP1 + LV2011SP1 on WinXP+Win7+cRIO
Kudos are welcome