ARTIFICIAL INTELLIGENCE APPARATUS FOR RECOGNIZING SPEECH OF USER USING PERSONALIZED LANGUAGE MODEL AND METHOD FOR THE SAME

摘要

According to an embodiment of the present invention, an artificial intelligence apparatus for recognizing a voice of a user comprises: a memory; a microphone; and a processor receiving a sound signal corresponding to an utterance voice of a user through the microphone, obtaining personalized identification information corresponding to the utterance voice, recognizing the utterance voice from the sound signal using a global language model, calculating the reliability of the recognition, and updating a personalized language model corresponding to the personalized identification information using the voice recognition result when the calculated reliability exceeds a first predetermined reference value.