公开(公告)号：US10528835B2

公开(公告)日：2020-01-07

申请号：US14573681

申请日：2014-12-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yong-wook Shin ,  Ki-jun Jeong ,  Chi-sang Jung

IPC: G06K9/00 ,  H04N21/4223 ,  H04N21/4415 ,  H04N21/466

Abstract: An image processing apparatus includes: a user input interface configured to provide a user input according to at least one input method; a storage configured to store a database for biometric information of at least one user which corresponds with at least one identification (IDs) previously registered to the image processing apparatus; a signal processor configured to process a preset service which is provided corresponding to an authenticated identification (ID) in response to a user being authenticated with the ID; and a controller configured to determine whether authentication is performed with regard to one of the IDs in response to an event occurring which identifies a current user, and retrieve and authenticate the ID from the database based on the biometric information of the current user acquired by the user input interface in response to determining that the authentication is not performed with regard to the ID.

公开(公告)号：US10553219B2

公开(公告)日：2020-02-04

申请号：US15213599

申请日：2016-07-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chi-sang Jung

IPC: G10L17/00 ,  G10L17/22 ,  G10L15/01 ,  G10L17/02 ,  G10L15/30 ,  G10L17/08 ,  G10L15/22

Abstract: A voice recognition apparatus, a voice recognition method, and a non-transitory computer readable recording medium are provided. The voice recognition apparatus includes a storage configured to store a preset threshold value for voice recognition; a voice receiver configured to receive a voice signal of an uttered voice; and a voice recognition processor configured to recognize a voice recognition starting word from the received voice signal, perform the voice recognition on the voice signal in response to a similarity score, which represents a recognition result of the recognized voice recognition starting word, being greater than or equal to the stored preset threshold value, and change the preset threshold value based on the recognition result of the voice recognition starting word.

公开(公告)号：US09804822B2

公开(公告)日：2017-10-31

申请号：US14698126

申请日：2015-04-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chi-sang Jung ,  Byung-jin Hwang

IPC: G10L25/00 ,  G10L25/27 ,  G06F3/16 ,  G10L17/20 ,  G10L15/00 ,  G10L17/08

CPC classification number: G06F3/167 ,  G10L15/00 ,  G10L17/08 ,  G10L17/20

Abstract: An electronic apparatus and a controlling methods thereof are disclosed. The electronic apparatus includes a voice input unit configured to receive a user voice, a storage unit configured to store a plurality of voice print feature models representing a plurality of user voices and a plurality of utterance environment models representing a plurality of environmental disturbances, a controller, in response to a user voice being input through the voice input unit, configured to extract utterance environment information of an utterance environment model among the plurality of utterance environment models corresponding to a location where the user voice is input, compare a voice print feature of the input user voice with the plurality of voice print feature models, revise a result of the comparison based on the extracted utterance environment information, and recognize a user corresponding to the input user voice based on the revised result.

公开(公告)号：US09484029B2

公开(公告)日：2016-11-01

申请号：US14670724

申请日：2015-03-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chi-sang Jung ,  Byung-jin Hwang

IPC: G10L15/00 ,  G10L15/22 ,  G10L17/02 ,  G10L15/06 ,  G10L15/02 ,  G10L15/26 ,  G10L17/06 ,  G10L15/08

CPC classification number: G10L15/22 ,  G10L15/063 ,  G10L15/265 ,  G10L17/02 ,  G10L17/06 ,  G10L2015/025 ,  G10L2015/0638 ,  G10L2015/088 ,  G10L2015/223

Abstract: An electronic apparatus and a method of speech recognition thereof are disclosed. According to the method of speech recognition of the electronic apparatus, the method includes receiving a speech of a speaker, extracting phonemic characteristics for recognizing a speech and voice print characteristics for registering the speaker by analyzing the received speech of the speaker, and in response to the speech of the speaker corresponding a registered trigger word or phrase, based on the extracted phonemic characteristics, changing an execution mode to a speech recognition mode of the electronic apparatus and registering the extracted voice print characteristics as voice print characteristics of the speaker who spoke the speech.

Abstract translation: 公开了一种电子设备及其语音识别方法。 根据电子装置的语音识别方法，该方法包括：接收讲话者的语音，提取用于识别语音的音素特征和语音打印特征，用于通过分析讲话者的接收到的语音来注册讲话者，并且响应于 基于所提取的音素特征，讲话者对应于已注册的触发词或短语的语音将执行模式改变为电子设备的语音识别模式，并将所提取的语音打印特征注册为讲话者的语音打印特征 言语。