recognize voice in unity

hello, i want to make a game that gets user voice as input. i want to check if a specific phrase is said or not, i tried many ways but what i want differs from what is implemented until now.

FIRST, i want some unknown words being detected, for example, "aaale" Or, "saab". so i need to detect some words (yes, they are not really "WORDs") using pronunciation i specify.

SECOND, i dont want to work only with windows, i know that window platform has a UnityEngine.Windows.Speech that does what i want. but i want to do this in all platform, specially android.

any suggestion will be helpful, thanks in advance.