SERVER METHOD AND COMPUTER PROGRAM FOR GENERATING FACIAL EXPRESSION OF AVATAR

An object of the present invention is to acquire a natural facial expression of an avatar that satisfies input voice data and target style data for avatar generation. A server that generates facial expression of an avatar comprises: a model learning unit for learning a landmark-based basic model and...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	CHOI YOUNG JU, KIM WOO YEUN, JO JI EUN, NAM YOON JI, HUH YOON BUM
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	ACOUSTICS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC DIGITAL DATA PROCESSING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	An object of the present invention is to acquire a natural facial expression of an avatar that satisfies input voice data and target style data for avatar generation. A server that generates facial expression of an avatar comprises: a model learning unit for learning a landmark-based basic model and at least one sub-model based on a plurality of learning data; an input unit for receiving voice data and purpose style data for generating an avatar; a derivation unit for deriving basic landmark information for an avatar corresponding to voice data based on the basic model; an adjustment unit that adjusts basic landmark information to reflect target style data based on the sub-model; and an output unit that outputs facial expression of the avatar based on the adjusted basic landmark information. 아바타의 얼굴 표정을 생성하는 서버는 복수의 학습 데이터에 기초하여 랜드마크 기반의 기초 모델 및 적어도 하나의 서브 모델을 학습하는 모델 학습부, 아바타를 생성하기 위한 음성 데이터 및 목적 스타일 데이터를 입력받은 입력부, 기초 모델에 기초하여 음성 데이터에 해당하는 아바타에 대한 기본 랜드마크 정보를 도출하는 도출부, 서브 모델에 기초하여 목적 스타일 데이터가 반영되도록 기본 랜드마크 정보를 조정하는 조정부 및 조정된 기본 랜드마크 정보에 기초하여 아바타의 얼굴 표정을 출력하는 출력부를 포함할 수 있다.