公开(公告)号：EP3355304A1

公开(公告)日：2018-08-01

申请号：EP18154072.5

申请日：2018-01-30

申请人： Samsung Electronics Co., Ltd.

发明人： Park, Jun Hyung ,  Park, No Joon ,  Lee, Hyo Jung ,  Lee, Tae Hee ,  Kim, Geon Soo ,  Kim, Han Jib ,  Jeon, Yong Joon

IPC分类号： G10L15/22 ,  G10L17/00 ,  G10L17/10

CPC分类号： G10L17/22 ,  G06F21/32 ,  G10L15/22 ,  G10L15/265 ,  G10L17/00 ,  G10L17/06 ,  G10L17/10 ,  G10L2015/223

摘要： An electronic device is provided. The electronic device includes a microphone configured to receive a voice, communication circuitry configured to communicate with an external electronic device, a memory, and a processor operatively connected to the microphone, the communication circuitry, and the memory. The memory stores instructions that, when executed by the processor, cause the electronic device to perform voice recognition for voice data corresponding to the voice, and determine whether to perform voiceprint recognition for the voice data based on whether a first expression is included in a result of the voice recognition.

公开(公告)号：EP3324404A1

公开(公告)日：2018-05-23

申请号：EP17205856.2

申请日：2013-05-08

申请人： Sony Mobile Communications AB

发明人： TOKUTAKE, Kenji

IPC分类号： G10L15/00 ,  G06F1/32 ,  G06F3/16 ,  G10L15/08 ,  G10L17/00

CPC分类号： G10L15/22 ,  G06F1/3215 ,  G06F1/325 ,  G06F1/3293 ,  G06F3/167 ,  G10L15/00 ,  G10L17/00 ,  G10L2015/088 ,  Y02D10/122

摘要： An information processing apparatus that detects a voice command via a microphone in order to activate the device and execute certain applications. The apparatus comprises a digital signal processor (DSP) and a host controller which are responsible for processing the voice commands. The DSP recognizes and processes voice commands intermittently while the host processor is in a sleep state, thereby reducing the overall power consumption of the apparatus. Further, when the DSP is configured to recognize voice commands intended only to activate the device, a memory having a sufficiently lower storage capacity suffices.

公开(公告)号：EP3319084A1

公开(公告)日：2018-05-09

申请号：EP17200111.7

申请日：2017-11-06

申请人： Intellisist, Inc.

发明人： ODINAK, Gilad ,  CARMIEL, Yishay

IPC分类号： G10L17/00

CPC分类号： G10L17/02 ,  G06F21/32 ,  G10L17/00 ,  G10L17/005 ,  G10L17/20 ,  G10L17/24

摘要： Caller identity verification can be improved by employing a multi-step verification that leverages speech features (28, 30) that are obtained from multiple interactions with a caller. An enrollment is performed in which customer speech features (23) and customer information are collected. When a caller calls into the call center (11), an attempt is made to verify the caller's identity by requesting the caller to speak a predefined phrase, extracting speech features from the spoken phrase, and comparing the phrase. If the purported identity (14) of the caller can be matched with one of the customers based on the comparison, the identity of the caller is verified. If the match cannot be made with a high enough degree of confidence, the customer is asked to speak any phrase that is not predefined. Features (30) are extracted from the caller's speech, combined with features (28) previously extracted from the predefined speech, and compared to the enrollment features (23).

摘要翻译： 主叫身份验证可以通过采用多步验证来提高，该验证利用了与呼叫者的多次交互中获得的语​​音特征（28,30）。 执行登记，收集客户语音特征（23）和客户信息。 当呼叫者呼入呼叫中心（11）时，试图通过请求呼叫者说出预定义的短语，从口头短语中提取语音特征并比较短语来验证呼叫者的身份。 如果根据比较可以将呼叫者的声称的身份（14）与其中一个顾客匹配，则确认呼叫者的身份。 如果不能以足够高的置信度进行比赛，则要求客户说出任何未预定义的短语。 从呼叫者的语音中提取特征（30），并结合先前从预定义语音中提取的特征（28），并与登记特征（23）进行比较。

公开(公告)号：EP3252755A1

公开(公告)日：2017-12-06

申请号：EP16767740.0

申请日：2016-03-21

申请人： ZTE Corporation

发明人： YAO, Lizhe ,  CHEN, Jun ,  SHANG, Guoqiang

IPC分类号： G10L17/00 ,  G06F21/32 ,  H04L9/32 ,  G06F21/46

CPC分类号： H04L63/0861 ,  G06F21/32 ,  G06F21/46 ,  G06F2221/2113 ,  G10L17/00 ,  G10L17/04 ,  G10L17/06 ,  G10L17/24 ,  H04L9/32 ,  H04L63/105 ,  H04W12/06 ,  H04W12/08

摘要： Provided are a method and apparatus for managing a graded cipher. The method includes that: a corresponding relationship between different security grades and corresponding voice passwords is established, herein the voice password corresponding to each security grade in the corresponding relationship is a part or all of a preset voice password; and a voice password is received from a user, and the obtained corresponding relationship is searched for the security grade corresponding to the voice password matched with the received voice password.

摘要翻译： 提供了一种管理分级密码的方法和装置。 该方法包括：建立不同安全等级与对应语音密码的对应关系，此时对应关系中每个安全等级对应的语音密码为预设语音密码的部分或全部; 并从用户接收语音密码，并查找得到的对应关系，查找与接收到的语音密码匹配的语音密码对应的安全等级。

公开(公告)号：EP3156978A1

公开(公告)日：2017-04-19

申请号：EP15461566.0

申请日：2015-10-14

申请人： Samsung Electronics Polska Sp. z o.o.

发明人： Bronakowski, Lukasz ,  Chochowski, Marcin ,  Gajewska-Dendek, Elzbieta ,  Tkaczuk, Jakub

IPC分类号： G07C9/00 ,  G10L17/00

CPC分类号： G07C9/00158 ,  G07C2209/14 ,  G10L17/04 ,  G10L17/24 ,  G10L25/18 ,  G10L25/21 ,  G10L25/93

摘要： A method for secure speaker verification, the method comprising the steps of: generating (501) a random, textual prompt for a user to speak; awaiting (502) for a user to speak the generated, textual prompt and recording the corresponding speech; in parallel to said speech recording (502), recording (503) ultrasound signals reflected from the user's face; subjecting (504) the recorded speech to automatic speech recognition in order to obtain a textual representation of the speech; detecting (505) user's liveness based on a correspondence of said recorded audio signal with said recorded ultrasound signal as well as based on the automatically recognized speech; executing (506) a text accuracy validation on said recorded speech subjected to the automatic speech recognition in comparison to the generated, textual prompt; and executing an authentication (507) of the user based on results of said detecting (505) user's liveness, and said text accuracy validation in order to verify whether the user was speaking the generated prompt, at the time of recording.

摘要翻译： 一种用于安全说话人验证的方法，所述方法包括以下步骤：产生（501）用于说话的随机，文本提示; 等待（502）使用户说出生成的文本提示并记录相应的语音; 与所述语音记录（502）并行地记录（503）从用户脸部反射的超声信号; 对所记录的语音进行自动语音识别（504）以获得语音的文本表示; 基于所述记录的音频信号与所述记录的超声信号的对应关系以及基于所述自动识别的语音来检测（505）用户的活动性; 与生成的文本提示相比，执行（506）对所述记录的语音进行自动语音识别的文本精确度验证; 以及基于所述检测（505）用户的活动性的结果和所述文本精确度验证来执行用户的认证（507），以便在记录时验证用户是否正在说出生成的提示。

公开(公告)号：EP3107089A1

公开(公告)日：2016-12-21

申请号：EP15172677.5

申请日：2015-06-18

申请人： Airbus Operations GmbH

发明人： KLOSE, Peter ,  LUEDTKE, Michael

IPC分类号： G10L15/26 ,  G10L17/00

CPC分类号： G10L17/06 ,  B64D11/0015 ,  G10L15/063 ,  G10L15/22 ,  G10L15/26 ,  G10L17/00 ,  G10L2015/0635 ,  G10L2015/227

摘要： The present disclosure relates to a method of performing speech recognition on board of an aircraft, to a computer program for executing the method, as well as to a speech recognition unit for performing speech recognition on board of an aircraft. The method comprises: receiving (S202) a speech signal spoken by a user; performing speaker recognition (S204) on the speech signal to identify the user from the speech signal; selecting (S206) a speech recognition user profile which is associated with the identified user; and performing speech recognition (S208) on the speech signal using the selected user profile.

摘要翻译： 本公开涉及一种在飞机上执行语音识别的方法，用于执行该方法的计算机程序以及用于在飞机上执行语音识别的语音识别单元。 该方法包括：接收（S202）由用户发出的语音信号; 对所述语音信号执行说话者识别（S204），以从所述语音信号中识别所述用户; 选择（S206）与所识别的用户相关联的语音识别用户简档; 以及使用所选择的用户简档对语音信号执行语音识别（S208）。

公开(公告)号：EP2364495B1

公开(公告)日：2016-10-12

申请号：EP08875076.5

申请日：2008-12-10

申请人： Agnitio S.L.

发明人： SANCHEZ ASENJO, Marta ,  GUTIERREZ, Alfredo ,  MARTIN DE LOS SANTOS DE LAS HERAS, Alberto ,  GARCIA GOMAR, Marta

IPC分类号： G10L17/00

CPC分类号： G10L17/00 ,  B66B13/26 ,  G10L17/02 ,  G10L17/06 ,  G10L17/24 ,  G10L17/26

摘要： The present invention refers to a method for verifying the identity of a speaker based on the speakers voice comprising the steps of: a) receiving a voice utterance; b) using biometric voice data to verify (10) that the speakers voice corresponds to the speaker the identity of which is to be verified based on the received voice utterance; and c) verifying (12, 13) that the received voice utterance is not falsified, preferably after having verified the speakers voice; d) accepting (16) the speakers identity to be verified in case that both verification steps give a positive result and not accepting (15) the speakers identity to be verified if any of the verification steps give a negative result. The invention further refers to a corresponding computer readable medium and a computer.

摘要翻译： 本发明涉及一种用于验证基于所述发言者的声音，其包括以下步骤的扬声器的特征：a）接收一个语音发声; b）使用生物特征的语音数据来验证（10）做了扬声器的语音对应于扬声器的所有身份这是基于所接收到的语音发声待验证; 和c）验证（12，13），管芯DASS接收的语音发声未被伪造，优选已经验证扬声器声音之后; D）接受（16）扬声器同一性的情况下，也都验证步骤给出阳性结果，而不是接受（15）扬声器的身份，如果任何的验证步骤得到了否定的结果，以进行验证进行验证。 本发明还涉及一种相应的计算机可读介质和计算机。

公开(公告)号：EP2945090A4

公开(公告)日：2016-08-17

申请号：EP14738232

申请日：2014-01-09

申请人： NEC CORP

发明人： SHIMA YOSHIKAZU

IPC分类号： G06F21/32 ,  G07C9/00 ,  G10L15/00 ,  G10L15/07 ,  G10L15/22 ,  G10L17/00 ,  G10L17/22

CPC分类号： G10L15/07 ,  G06F3/167 ,  G06F21/32 ,  G07C9/00087 ,  G10L17/00 ,  G10L17/22 ,  G10L2015/223

摘要： A terminal comprises: speech receiving means that receives speech in a locked state; voiceprint authentication means that performs voiceprint authentication based on the speech received in the locked state and determining whether or not a user is legitimate; speech recognition means that performs speech recognition of the speech received in the locked state; and execution means that executes an application using a result of the speech recognition. It is possible to easily unlock the terminal having the voiceprint authentication and speech recognition functions.

公开(公告)号：EP2595031A3

公开(公告)日：2016-01-06

申请号：EP12193040.8

申请日：2012-11-16

申请人： Samsung Electronics Co., Ltd

发明人： Kim, Sang-yoon ,  Ryu, Hee-seob ,  Park, Kyung-mi ,  Jeong, Ki-jun ,  Park, Seung-kwon

IPC分类号： G06F3/01 ,  G06F3/03 ,  G06F3/16 ,  G06F21/32 ,  H04N21/4223 ,  H04N21/4415 ,  H04N21/442 ,  G10L17/00

CPC分类号： G06F3/167 ,  G06F3/01 ,  G06F3/012 ,  G06F3/017 ,  G06F3/0304 ,  G06F21/32 ,  G06K9/00288 ,  G06K9/00362 ,  G10L15/22 ,  G10L17/22 ,  G10L2015/223 ,  H04N21/4223 ,  H04N21/4415 ,  H04N21/44218

摘要： Disclosed are a display apparatus and a control method thereof, the display apparatus including: an image acquirer which acquires an image of a plurality of users; a display which displays the image acquired by the image acquirer; and a controller which selects a user making a predetermined gesture among the plurality of users in the image and controls the display apparatus to perform an operation corresponding to the selected user out of operations which are capable of being performed by the display apparatus when the image of the plurality of users is acquired through the image acquirer and the predetermined gesture is recognized from the acquired image.

公开(公告)号：EP2945090A1

公开(公告)日：2015-11-18

申请号：EP14738232.9

申请日：2014-01-09

申请人： NEC CORPORATION

发明人： SHIMA, Yoshikazu

IPC分类号： G06F21/32 ,  G10L15/00 ,  G10L17/00

CPC分类号： G10L15/07 ,  G06F3/167 ,  G06F21/32 ,  G07C9/00087 ,  G10L17/00 ,  G10L17/22 ,  G10L2015/223

摘要： A terminal comprises: speech receiving means that receives speech in a locked state; voiceprint authentication means that performs voiceprint authentication based on the speech received in the locked state and determining whether or not a user is legitimate; speech recognition means that performs speech recognition of the speech received in the locked state; and execution means that executes an application using a result of the speech recognition. It is possible to easily unlock the terminal having the voiceprint authentication and speech recognition functions.

摘要翻译： 终端包括：语音接收装置，其在锁定状态下接收语音; 声纹认证意味着基于在锁定状态下接收的语音执行声纹认证，并确定用户是否合法; 语音识别装置执行在锁定状态下接收到的语音的语音识别; 以及执行装置，其使用语音识别的结果来执行应用。 可以容易地解锁具有声纹认证和语音识别功能的终端。