公开(公告)号：US20210142800A1

公开(公告)日：2021-05-13

申请号：US16851053

申请日：2020-04-16

Applicant: LG ELECTRONICS INC.

Inventor： Siyoung YANG ,  Yongchul Park ,  Sungmin Han ,  Sangki Kim ,  Juyeong Jang ,  Minook Kim

IPC: G10L15/22 ,  G10L15/06 ,  G06F3/14 ,  G06N3/08 ,  G06N3/04

Abstract: Disclosed is an apparatus for processing a voice signal. The apparatus comprises a receiver, a memory, and a processor. The apparatus may execute an artificial intelligence (AI) algorithm and/or a machine learning algorithm and may communicate with other electronic devices in a 5G communication environment. Accordingly, convenience of a user may be enhanced.

公开(公告)号：US10937412B2

公开(公告)日：2021-03-02

申请号：US16268333

申请日：2019-02-05

Applicant: LG ELECTRONICS INC.

Inventor： Jonghoon Chae ,  Sungmin Han ,  Yongchul Park ,  Siyoung Yang ,  Juyeong Jang

IPC: G10L13/00 ,  G10L13/10 ,  G10L13/047 ,  G10L13/08

Abstract: According to an embodiment of the present invention, there is provided a terminal including a memory which stores a prosody correction model; a processor which corrects a first prosody prediction result of a text sentence to a second prosody prediction result based on the prosody correction model and generates a synthetic speech corresponding to the text sentence having a prosody according to the second prosody prediction result; and an audio output unit which outputs the generated synthetic speech.