ASRautomatic speech recognition ELECTRONIC DEVICE FOR GENERATING PERSONAL AUTOMATIC SPEECH RECOGNITION MODEL AND METHOD FOR OPERATING THE SAME

摘要

According to various embodiments of the present invention, an electronic device includes: a processor; and a memory electrically connected with the processor. The memory can store instructions executed to enable the processor to store text data, which are created by recognizing voice data of a user through a given automatic speech recognition (ASR) model, in a speech data storage, which is functionally connected with the processor, as one single speech datum along with the voice data, to obtain a candidate replacing an ASR error part from a plurality of speech data stored in the speech data storage, to create a personalized ASR model by deep-learning of the ASR model based on the candidate and the voice data of the user corresponding to the candidate, to receive a reaction of the user to the candidate through an input device which is functionally connected with the processor, and to update the ASR model to the personalized ASR model based on the reaction of the user. Besides, various embodiments are possible.