公开(公告)号：US20180308483A1

公开(公告)日：2018-10-25

申请号：US15959930

申请日：2018-04-23

Applicant: LG ELECTRONICS INC.

Inventor： Nomin Myoung ,  Jaewoo Kim ,  Yeonho Park

IPC: G10L15/22 ,  G10L15/30 ,  G10L13/04

CPC classification number: G10L15/22 ,  G10L15/265

Abstract: Disclosed is a voice recognition apparatus including: an audio input unit configured to receiving a voice; a communication module configured to transmit voice data received from the audio input unit to a server system which performs voice recognition processing, and receive recognition result data on the voice data from the server system; and a controller configured to control the audio input unit and the communication module, wherein, when first voice data is received, the controller perform control to transmit the first voice data to the server system, and wherein, when the first voice data is a conversation command, the controller performs control to receive a first audible answer message including a first question from the server system and output the first audible answer message. In this manner, voice recognition may be performed efficiently.

公开(公告)号：US10692499B2

公开(公告)日：2020-06-23

申请号：US15959961

申请日：2018-04-23

Applicant: LG ELECTRONICS INC.

Inventor： Suhee Lim ,  Joongeon Park ,  Yeonho Park ,  Sukyoung Lyu

IPC: G10L15/30 ,  G10L15/22 ,  G10L15/26 ,  G10L15/18 ,  G10L15/08

Abstract: Disclosed is an artificial intelligence voice recognition apparatus including: an audio input unit configured to receive a voice; a communication module configured to transmit voice data received from the audio input unit to a server system, which performs voice recognition processing, and receive recognition result data on the voice data from the server system; and a controller configured to control the audio input unit and the communication module, wherein, when a voice command in the voice data corresponds to a pre-stored keyword command, the controller performs control to perform an operation corresponding to the keyword command, and wherein when the voice command in the voice data does not correspond to the pre-stored keyword command, the controller performs control to transmit the voice data including the voice command to the server system. Accordingly, voice recognition may be performed efficiently.