Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020196978 - ELECTRONIC DEVICE FOR MULTI-SCALE VOICE EMOTION RECOGNITION AND OPERATION METHOD OF SAME

Publication Number WO/2020/196978
Publication Date 01.10.2020
International Application No. PCT/KR2019/004269
International Filing Date 10.04.2019
IPC
G10L 25/63 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
63for estimating an emotional state
G10L 15/02 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
02Feature extraction for speech recognition; Selection of recognition unit
G10L 21/02 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
G10L 21/04 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
04Time compression or expansion
Applicants
  • 한국과학기술원 KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY [KR]/[KR]
Inventors
  • 이수영 LEE, Soo-Young
  • 최신국 CHOI, Shinkook
  • 신영훈 SHIN, Young Hoon
  • 김태호 KIM, Taeho
  • 김태훈 KIM, Taehun
Agents
  • 양성보 YANG, Sungbo
Priority Data
10-2019-003360725.03.2019KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) ELECTRONIC DEVICE FOR MULTI-SCALE VOICE EMOTION RECOGNITION AND OPERATION METHOD OF SAME
(FR) DISPOSITIF ÉLECTRONIQUE POUR LA RECONNAISSANCE D'ÉMOTIONS VOCALES À ÉCHELLES MULTIPLES ET SON PROCÉDÉ DE FONCTIONNEMENT
(KO) 멀티스케일 음성 감정 인식을 위한 전자 장치 및 그의 동작 방법
Abstract
(EN)
An electronic device and an operation method of same according to various embodiments are for multi-scale voice emotion recognition, and may be configured to: compress a voice signal into a plurality of scales; impart weights according to attention in correspondence to the respective scales; extract voice features of the voice signal from the scales on the basis of the weights; and recognize emotion in the voice signal on the basis of the voice features.
(FR)
Selon divers modes de réalisation, l'invention concerne un dispositif électronique et son procédé de fonctionnement qui sont destinés à la reconnaissance d'émotions vocales à échelles multiples et peuvent être conçus pour : compresser un signal vocal en une pluralité d'échelles ; transmettre des pondérations en fonction de l'attention en correspondance avec les échelles respectives ; extraire des caractéristiques vocales du signal vocal à partir des échelles sur la base des pondérations ; et reconnaître une émotion dans le signal vocal sur la base des caractéristiques vocales.
(KO)
다양한 실시예들에 따른 전자 장치 및 그의 동작 방법은 멀티스케일 음성 감정 인식을 위한 것으로, 음성 신호를 복수 개의 스케일들로 압축하고, 스케일들 각각에 대응하여, 주의집중(attention)에 따른 가중치를 부여하고, 스케일들로부터, 가중치를 기반으로 음성 신호의 음성 특징을 추출하고, 음성 특징에 기반하여, 음성 신호의 감정을 인식하도록 구성될 수 있다.
Latest bibliographic data on file with the International Bureau