METHOD FOR GENERATING HEAD MODEL ANIMATION FROM VOICE SIGNAL, AND ELECTRONIC DEVICE FOR IMPLEMENTING SAME

WIPO Patent Application WO/2021/112365

A1

Disclosed are: a method for generating a head model animation from a voice signal using an artificial intelligence model; and an electronic device for implementing same. The disclosed method for generating a head model animation from a voice signal, carried out by the electronic device, comprises the steps of: acquiring characteristics information of a voice signal from the voice signal; by using the artificial intelligence model, acquiring, from the characteristics information, a phoneme stream corresponding to the voice signal, and a viseme stream corresponding to the phoneme stream; by using the artificial intelligence model, acquiring an animation curve of visemes included in the viseme stream; merging the phoneme stream with the viseme stream; and generating a head model animation by applying the animation curve to the visemes of the merged phoneme and viseme stream.

GLAZISTOV IVAN VICTOROVICH (RU)
KROTOV ILYA IGOREVICH (RU)
NURLANOV ZHAKSHYLYK NURLANOVICH (KG)
KARACHAROV IVAN OLEGOVICH (RU)
SIMUTIN ALEKSANDR VLADISLAVOVICH (RU)
DANILEVICH ALEXEY BRONISLAVOVICH (RU)

PCT/KR2020/009663

June 10, 2021

July 22, 2020

Click for automatic bibliography generation  

SAMSUNG ELECTRONICS CO LTD (KR)

G06T13/40; G06N3/08; G06N3/12; G06T7/20; G06T7/33; G10L15/02; G10L15/26; G10L21/06; G10L25/30

KR20060090687A	2006-08-14
US20170243387A1	2017-08-24
US20170011745A1	2017-01-12
KR20190084260A	2019-07-16
US20090135177A1	2009-05-28

Y.P.LEE, MOCK & PARTNERS (KR)

View/Download PDF      PDF Help

Previous Patent: BATTERY MODULE AND BATTERY PACK INCLUDING SAME

Next Patent: VIEWING ANGLE FILTER AND DISPLAY DEVICE INCLUDING SAME