Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021060573 - IMAGE DISPLAY DEVICE AND VOICE RECOGNITION METHOD THEREFOR

Publication Number WO/2021/060573
Publication Date 01.04.2021
International Application No. PCT/KR2019/012380
International Filing Date 24.09.2019
IPC
G10L 17/24 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
22Interactive procedures; Man-machine interfaces
24 the user being prompted to utter a password or a predefined phrase
G10L 15/22 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialog
G10L 15/04 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
04Segmentation; Word boundary detection
G06F 3/16 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
3Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
16Sound input; Sound output
G06F 1/32 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
1Details not covered by groups G06F3/-G06F13/82
26Power supply means, e.g. regulation thereof
32Means for saving power
CPC
G06F 1/32
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
1Details not covered by groups G06F3/00G06F13/00 and G06F21/00
26Power supply means, e.g. regulation thereof
32Means for saving power
G06F 3/16
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
3Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
16Sound input; Sound output
G10L 15/04
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
04Segmentation; Word boundary detection
G10L 15/22
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialogue
G10L 17/24
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
22Interactive procedures; Man-machine interfaces
24the user being prompted to utter a password or a predefined phrase
Applicants
  • 엘지전자 주식회사 LG ELECTRONICS INC. [KR]/[KR]
Inventors
  • 최우진 CHOI, Woo Jin
  • 김성은 KIM, Sung Eun
  • 박현우 PARK, Hyun Woo
  • 정은경 JUNG, Eun Kyung
  • 채대곤 CHAE, Dae Gon
Agents
  • 특허법인 남촌 NAMCHON PATENT AND LAW FIRM
Priority Data
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) IMAGE DISPLAY DEVICE AND VOICE RECOGNITION METHOD THEREFOR
(FR) DISPOSITIF D'AFFICHAGE D'IMAGE ET SON PROCÉDÉ DE RECONNAISSANCE VOCALE
(KO) 영상표시장치 및 이의 음성 인식 방법
Abstract
(EN)
An image display device and a voice recognition method, according to one embodiment of the present invention, store received first speech data in a first buffer when a trigger word is recognized from speech data, store, in a second buffer, second speech data continuously spoken by a user, store, in a third buffer, third speech data continuously spoken by the user when the trigger word is successfully verified on the basis of the first speech data after an operating system is completely booted, and perform voice recognition on speech data continuously spoken by the user by connecting the second speech data and the third speech data stored in the second buffer and the third buffer, respectively. Therefore, instructions spoken, at intervals, after a trigger word and instructions continuously spoken by a user can be recognized, and thus a predetermined pattern is not required when the user speaks the trigger word and instructions, and voice recognition can be performed with only the minimum power.
(FR)
L'invention concerne un dispositif d'affichage d'image et un procédé de reconnaissance vocale qui, selon un mode de réalisation, stockent des premières données de parole reçues dans un premier tampon lorsqu'un mot de déclenchement est reconnu à partir de données de parole, stockent, dans un deuxième tampon, des deuxièmes données de parole prononcées en continu par un utilisateur, stocke, dans un troisième tampon, des troisième données de parole prononcées en continu par l'utilisateur lorsque le mot de déclenchement est vérifié avec succès sur la base des premières données de parole après que le système d'exploitation a été complètement démarré et effectue une reconnaissance vocale sur des données de parole prononcées en continu par l'utilisateur en reliant les deuxièmes données de parole et les troisièmes données de parole stockées respectivement dans le deuxième tampon et le troisième tampon. Par conséquent, des instructions prononcées, à des intervalles, après un mot de déclenchement et des instructions prononcées en continu par un utilisateur, peuvent être reconnues et ainsi un motif prédéfini n'est pas nécessaire lorsque l'utilisateur prononce le mot de déclenchement et les instructions et la reconnaissance vocale peut être effectuée avec seulement la puissance minimale.
(KO)
본 발명의 일 실시예에 따른 영상표시장치 및 이의 음성 인식 방법은 발화 데이터에서 기동어가 인식되면, 수신한 제1 발화 데이터를 제1 버퍼에 저장하고, 사용자로부터 연속 발화되는 제2 발화 데이터를 제2 버퍼에 저장하며, 운영체제 부팅 완료 후에 제1 발화 데이터에 기초하여 기동어 검증이 성공하면, 사용자로부터 연속 발화되는 제3 발화 데이터를 제3 버퍼에 저장하고, 제2 버퍼 및 제3 버퍼에 각각 저장된 제2 발화 데이터 및 제3 발화 데이터를 연결하여 사용자의 연속하여 발화되는 발화 데이터에 대한 음성인식을 수행한다. 이에 의해, 기동어 이후에 간격을 두고 발화하는 명령어를 비롯하여 연속하여 발화되는 사용자의 명령어를 인식할 수 있으므로 사용자에게 기동어 및 명령어 발화에 있어서 일정 패턴을 요구하지 않아도 되며, 최소한의 전력만으로도 음성인식을 수행할 수 있다.
Latest bibliographic data on file with the International Bureau