Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020196979 - ELECTRONIC DEVICE FOR CHARACTERISTICS-CONTROLLABLE SPEECH IMITATION AND OPERATION METHOD THEREOF

Publication Number WO/2020/196979
Publication Date 01.10.2020
International Application No. PCT/KR2019/004270
International Filing Date 10.04.2019
IPC
G10L 13/033 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
02Methods for producing synthetic speech; Speech synthesisers
033Voice editing, e.g. manipulating the voice of the synthesiser
G10L 13/08 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
08Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
G10L 17/02 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
02Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis or principal components; Feature selection or extraction
G10L 25/51 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/-G10L21/129
48specially adapted for particular use
51for comparison or discrimination
G10L 25/30 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/-G10L21/129
27characterised by the analysis technique
30using neural networks
Applicants
  • 한국과학기술원 KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY [KR]/[KR]
Inventors
  • 이수영 LEE, Soo-Young
  • 김태호 KIM, Taeho
  • 신영훈 SHIN, Young Hoon
  • 최신국 CHOI, Shinkook
  • 김태훈 KIM, Taehun
  • 라비아잠 RABIEE, Azam
Agents
  • 양성보 YANG, Sungbo
Priority Data
10-2019-003340325.03.2019KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) ELECTRONIC DEVICE FOR CHARACTERISTICS-CONTROLLABLE SPEECH IMITATION AND OPERATION METHOD THEREOF
(FR) DISPOSITIF ÉLECTRONIQUE POUR UNE IMITATION DE PAROLE POUVANT ÊTRE COMMANDÉE PAR DES CARACTÉRISTIQUES ET PROCÉDÉ DE FONCTIONNEMENT ASSOCIÉ
(KO) 특징 제어 가능 음성 모사를 위한 전자 장치 및 그의 동작 방법
Abstract
(EN)
An electronic device and an operation method thereof, according to various embodiments, are for characteristics-controllable speech imitation and may comprise: encoding text; inferring embedding information associated with characteristics information and a speech signal of a speaker; decoding the encoded text along with the inferred embedding information; and generating a speech signal.
(FR)
Selon divers modes de réalisation, l'invention concerne un dispositif électronique et son procédé de fonctionnement qui sont destinés à une imitation de parole pouvant être commandée par des caractéristiques et peuvent comprendre : le codage d'un texte ; la déduction d'informations d'incorporation associées à des informations de caractéristiques et à un signal de parole d'un locuteur ; le décodage du texte codé avec les informations d'incorporation déduites ; et la génération d'un signal de parole.
(KO)
다양한 실시예들에 따른 전자 장치 및 그의 동작 방법은 특징 제어 가능 음성 모사를 위한 것으로, 텍스트를 인코딩하고, 화자 음성 신호 및 특징 정보와 관련된 임베딩 정보를 추론하고, 인코딩된 텍스트를 추론된 임베딩 정보와 함께 디코딩하여, 음성 신호를 발생시키도록 구성될 수 있다.
Latest bibliographic data on file with the International Bureau