公开(公告)号：US20190385607A1

公开(公告)日：2019-12-19

申请号：US16553683

申请日：2019-08-28

Applicant: LG ELECTRONICS INC.

Inventor： Gyeonghun KIM ,  Yireun KIM

IPC: G10L15/22 ,  G10L25/84 ,  G10L15/28 ,  H04W4/70

Abstract: Provided are an intelligent voice output method, a voice output device and an intelligent computing device. An intelligent voice output method includes obtaining a voice from a plurality of voice output devices, selecting a device for a response to the voice, and controlling the response device based on recognition state information of the voice recognized by the response device so that the response device outputs the response. Accordingly, a response from a voice output device can be clearly delivered to a user. One or more of the voice output devices, intelligent computing devices, and servers of the present invention may include artificial intelligence modules, drones (Unmanned Aerial Vehicles, UAVs), robots, Augmented Reality (AR) devices, and virtual reality (VR) devices, devices related to 5G services, and the like.

公开(公告)号：US20190392816A1

公开(公告)日：2019-12-26

申请号：US16561777

申请日：2019-09-05

Applicant: LG ELECTRONICS INC.

Inventor： Yekyung KIM ,  Gyeonghun KIM ,  Yejin KIM

IPC: G10L15/06 ,  G10L15/22 ,  G10L15/16

Abstract: A speech processing method includes learning to obtain at least one region-specific weight information for each word included in an utterance of a speaker, and updating word embedding information based on the at least one region-specific weight information obtained for each of the word.