Say we took a mic input (say hello) and saved it as a wav file. Then we take the same hello input from the microphone. Now, if they are identical, we trigger an action. So, how do we compare and verify the input data of the two inputs?
Update: Suppose we want the exact word to be spoken and not interested in who said that word, as this will prevent the creation of the program / software. The user is independent. In other words: we need to issue an exact message from the user's microphone input, and then check whether it matches any of the given predefined commands, which in turn will trigger an action.
So, in other words, we need the following:
- extract the exact words spoken by the speaker / user.
- compare / check whether the word spoken by the user matches any stored predefined word.
So how do we find out about our business?
source
share