KEYWORD SPOTTING METHOD USING SUBUNIT SEQUENCE RECOGNITION

摘要

PURPOSE: A keyword detecting method using subunit recognition is provided to determine a keyword in a sound voice through the subunit recognition. CONSTITUTION: A feature parameters is extracted from a previously inputted voice for performing subunit recognition(S10). The subunit is a smaller unit than a keyword of a word or a sentence unit. By using sub unit recognizing device, a sub unit arrangement is extracted about a speech voice of a user(S20). A keyword is expressed in a subunit arrangement(S30). By comparing an expressed subunit arrangement and an extracted subunit arrangement, a keyword detection is determined(S40).