If you’ve got a spare few minutes this weekend why not sit down and replicate the DIY Voice Recognition System project from Xiaowen Lu and Shihjia Lee. Of course you’ll need to know about the Nyquist Rate Theorem, Chebychev filters and the Fourier Transform, but apart from that it should be a piece of cake, eh?
The project has not met our expectations fully, as we initially specified that the system would be able to recognize a sentence as a password. But we are more than happy that it is able to recognize a word as the password by more than 80%-90% of the time, depending on the choice of passwords. There is a training procedure that need to be implemented, which is an added feature to increase the accuracy of the security system. However, the system can still be used without training. In this case, there is a maximum of 5 words only.