公开(公告)号：WO2017136064A1

公开(公告)日：2017-08-10

申请号：PCT/US2016/068398

申请日：2016-12-22

Applicant: QUALCOMM INCORPORATED

Inventor： GUO, Yinyi ,  JIN, Minho ,  CHO, JunCheol ,  CHO, Yongwoo ,  KIM, Lae-Hoon ,  VISSER, Erik ,  ZHANG, Shuhua

IPC: H04L29/06 ,  G06F21/32 ,  H04W12/06

CPC classification number: G06F21/32 ,  G06F21/316 ,  G06F21/36 ,  G06F2221/2133 ,  H04L63/0861 ,  H04W12/06

Abstract: A device includes a memory and a processor. The memory is configured to store a threshold. The processor is configured to authenticate a user based on authentication data. The processor is also configured to, in response to determining that the user is authenticated, generate a correlation score indicating a correlation between a first signal received from a first sensor and a second signal received from a second sensor. The processor is also configured to determine liveness of the user based on a comparison of the correlation score and the threshold.

Abstract translation: 一个设备包括一个存储器和一个处理器。 内存配置为存储阈值。 处理器被配置为基于认证数据来认证用户。 处理器还被配置为响应于确定用户被认证，生成指示从第一传感器接收到的第一信号和从第二传感器接收到的第二信号之间的相关性的相关性分数。 处理器还被配置成基于相关分数和阈值的比较来确定用户的活跃度。

公开(公告)号：WO2016064556A1

公开(公告)日：2016-04-28

申请号：PCT/US2015/053665

申请日：2015-10-02

Applicant: QUALCOMM INCORPORATED

Inventor： MOON, Sunkuk ,  JIN, Minho ,  XIA, Haiying ,  HUANG, Hesu ,  DALE, Warren Frederick

IPC: G10L15/06

CPC classification number: G10L15/02 ,  G10L15/063 ,  G10L15/08 ,  G10L15/22 ,  G10L2015/022 ,  G10L2015/025 ,  G10L2015/027

Abstract: A method for verifying at least one sound sample to be used in generating a sound detection model in an electronic device includes receiving a first sound sample; extracting a first acoustic feature from the first sound sample; receiving a second sound sample; extracting a second acoustic feature from the second sound sample; and determining whether the second acoustic feature is similar to the first acoustic feature.

Abstract translation: 一种用于验证用于在电子设备中生成声音检测模型的至少一个声音样本的方法包括：接收第一声音样本; 从所述第一声音样本中提取第一声学特征; 接收第二个声音样本; 从所述第二声音样本中提取第二声学特征; 以及确定所述第二声学特征是否类似于所述第一声学特征。

公开(公告)号：WO2015041882A1

公开(公告)日：2015-03-26

申请号：PCT/US2014/054540

申请日：2014-09-08

Applicant: QUALCOMM INCORPORATED

Inventor： LEE, Minsub ,  KIM, Taesu ,  HWANG, Kyu Woong ,  JIN, Minho

IPC: G10L15/22

CPC classification number: G10L15/20 ,  G06F3/167 ,  G10L15/22 ,  G10L25/48 ,  G10L2015/228

Abstract: A method for activating a voice assistant function in a mobile device is disclosed. The method includes receiving an input sound stream by a sound sensor and determining a context of the mobile device. The method may determine the context based on the input sound stream. For determining the context, the method may also obtain data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device. In this method, a threshold for activating the voice assistant function is adjusted based on the context. The method detects a target keyword from the input sound stream based on the adjusted threshold. If the target keyword is detected, the method activates the voice assistant function.

Abstract translation: 公开了一种在移动设备中激活语音辅助功能的方法。 该方法包括通过声音传感器接收输入声音流并确定移动设备的上下文。 该方法可以基于输入声音流来确定上下文。 为了确定上下文，该方法还可以从加速度传感器，位置传感器，照明传感器，接近传感器，时钟单元和日历单元中的至少一个获取指示移动设备的上下文的数据。 移动设备。 在该方法中，基于上下文来调整用于激活语音辅助功能的阈值。 该方法基于调整后的阈值从输入声音流中检测目标关键字。 如果检测到目标关键字，则该方法激活语音辅助功能。

公开(公告)号：WO2014182458A1

公开(公告)日：2014-11-13

申请号：PCT/US2014/035241

申请日：2014-04-24

Applicant: QUALCOMM INCORPORATED

Inventor： YUN, Sungrack ,  JIN, Minho ,  KIM, Taesu ,  HWANG, Kyu Woong

IPC: G10L15/22 ,  G06F1/32 ,  G10L15/08 ,  G10L25/78 ,  H04W52/02

CPC classification number: G10L15/08 ,  G06F1/3206 ,  G06F1/325 ,  G06F3/167 ,  G10L15/22 ,  G10L25/78 ,  G10L2015/088 ,  H04M1/72522 ,  H04M2250/74 ,  H04W52/0254 ,  Y02D70/00 ,  Y02D70/1262 ,  Y02D70/1264

Abstract: A method for controlling voice activation by a target keyword in a mobile device is disclosed. The method includes receiving an input sound stream. When the input sound stream indicates speech, the voice activation unit is activated to detect the target keyword and at least one sound feature is extracted from the input sound stream. Further, the method includes deactivating the voice activation unit when the at least one sound feature indicates a non-target keyword.

Abstract translation: 公开了一种用于通过移动设备中的目标关键字来控制语音激活的方法。 该方法包括接收输入声音流。 当输入声音流指示语音时，激活语音激活单元以检测目标关键字，并且从输入声音流中提取至少一个声音特征。 此外，该方法包括当至少一个声音特征指示非目标关键字时，停用语音激活单元。

公开(公告)号：WO2013177022A1

公开(公告)日：2013-11-28

申请号：PCT/US2013/041778

申请日：2013-05-20

Applicant: QUALCOMM INCORPORATED

Inventor： SADASIVAM, Shankar ,  JIN, Minho ,  GROKOP, Leonard Henry ,  TEAGUE, Edward Harrison

IPC: G10L25/78 ,  G10L25/27

CPC classification number: G10L25/78 ,  G10L25/27

Abstract: Various arrangements for detecting a type of sound, such as speech, are presented. A plurality of audio snippets may be sampled. A period of time may elapse between consecutive audio snippets. A hypothetical test may be performed using the sampled plurality of audio snippets. Such a hypothetical test may include weighting one or more hypothetical values greater than one or more other hypothetical values. Each hypothetical value may correspond to an audio snippet of the plurality of audio snippets. The hypothetical test may further include using at least the greater weighted one or more hypothetical values to determine whether at least one audio snippet of the plurality of audio snippets comprises the type of sound.

Abstract translation: 呈现用于检测诸如语音之类的声音的各种布置。 可以对多个音频片段进行采样。 连续的音频片段之间可能会有一段时间。 可以使用采样的多个音频片段来执行假设测试。 这样的假设测试可以包括加权大于一个或多个其他假设值的一个或多个假设值。 每个假设值可以对应于多个音频片段的音频片段。 假设测试还可以包括使用至少较大加权的一个或多个假设值来确定多个音频片段中的至少一个音频片段是否包括声音的类型。

公开(公告)号：EP3210205B1

公开(公告)日：2020-05-27

申请号：EP15778583.3

申请日：2015-10-02

Applicant: Qualcomm Incorporated

Inventor： MOON, Sunkuk ,  JIN, Minho ,  XIA, Haiying ,  HUANG, Hesu ,  DALE, Warren Frederick

IPC: G10L15/06

公开(公告)号：EP3047482A1

公开(公告)日：2016-07-27

申请号：EP14784130.8

申请日：2014-09-08

Applicant: Qualcomm Incorporated

Inventor： LEE, Minsub ,  KIM, Taesu ,  HWANG, Kyu Woong ,  JIN, Minho

IPC: G10L15/22

CPC classification number: G10L15/20 ,  G06F3/167 ,  G10L15/22 ,  G10L25/48 ,  G10L2015/228

Abstract: A method for activating a voice assistant function in a mobile device is disclosed. The method includes receiving an input sound stream by a sound sensor and determining a context of the mobile device. The method may determine the context based on the input sound stream. For determining the context, the method may also obtain data indicative of the context of the mobile device from at least one of an acceleration sensor, a location sensor, an illumination sensor, a proximity sensor, a clock unit, and a calendar unit in the mobile device. In this method, a threshold for activating the voice assistant function is adjusted based on the context. The method detects a target keyword from the input sound stream based on the adjusted threshold. If the target keyword is detected, the method activates the voice assistant function.

公开(公告)号：EP2829087A1

公开(公告)日：2015-01-28

申请号：EP13707965.3

申请日：2013-02-15

Applicant: Qualcomm Incorporated

Inventor： JIN, Minho ,  KIM, Taesu ,  YOU, Kisun ,  CHO, Hyun-Mook ,  KOO, Hyung-Il ,  KIM, Duck-Hoon

IPC: H04W4/04 ,  G06F1/32

Abstract: A method for controlling an application in a mobile device is disclosed. The method includes receiving environmental information, inferring an environmental context from the environmental information, and controlling activation of the application based on a set of reference models associated with the inferred environmental context. In addition, the method may include receiving a sound input, extracting a sound feature from the sound input, transmitting the sound feature to a server configured to group a plurality of mobile devices into at least one similar context group, and receiving, from the server, information on a leader device or a non-leader device and the at least one similar context group.

Abstract translation: 公开了一种用于控制移动设备中的应用的方法。 该方法包括从环境信息中接收环境信息，推断环境背景，以及基于与推断的环境背景相关联的一组参考模型来控制应用的激活。 此外，该方法可以包括接收声音输入，从声音输入中提取声音特征，将声音特征发送到被配置为将多个移动设备分组成至少一个类似上下文组的服务器，以及从服务器 关于领导装置或非领导装置的信息以及至少一个类似的上下文组。

公开(公告)号：WO2016039947A1

公开(公告)日：2016-03-17

申请号：PCT/US2015/045725

申请日：2015-08-18

Applicant: QUALCOMM INCORPORATED

Inventor： KIM, Sungwoong ,  HWANG, Kyuwoong ,  KIM, Taesu ,  KIM, Duck Hoon ,  JIN, Minho ,  CHO, Yongwoo

IPC: H04W12/08 ,  H04W4/00 ,  H04W84/18

CPC classification number: G06F21/34 ,  G06F21/35 ,  H04W4/80 ,  H04W12/08 ,  H04W84/18

Abstract: A method, which is performed in a first electronic device, for authorizing access to a second electronic device is disclosed. The method may include establishing communication between the first electronic device and the second electronic device. The method may also obtain data indicative of a motion of at least one of the first and second electronic devices in response to a movement of the at least one of the first and second electronic devices. Based on the data, a control signal authorizing access to the second electronic device is generated, and transmitted to the second electronic device.

Abstract translation: 公开了一种在第一电子设备中执行的用于授权访问第二电子设备的方法。 该方法可以包括建立第一电子设备和第二电子设备之间的通信。 响应于第一和第二电子设备中的至少一个的移动，该方法还可以获得指示第一和第二电子设备中的至少一个的运动的数据。 基于该数据，生成授权访问第二电子设备的控制信号，并将其发送到第二电子设备。

公开(公告)号：WO2014182459A1

公开(公告)日：2014-11-13

申请号：PCT/US2014/035244

申请日：2014-04-24

Applicant: QUALCOMM INCORPORATED

Inventor： LEE, Minsub ,  KIM, Taesu ,  HWANG, KyuWoong ,  KIM, Sungwoong ,  JIN, Minho

IPC: G10L15/22 ,  G10L15/08

CPC classification number: G10L15/08 ,  G10L15/183 ,  G10L15/22 ,  G10L15/32

Abstract: A method of detecting a target keyword from an input sound for activating a function in a mobile device is disclosed. In this method sound features are extracted from the input stream and statistics are generated (340) including the mean value and the variance of a particular sound feature. Based on the statistics the method adaptively skips the normalisation of a sound feature when the difference between the present value and the previous value is not significant, this has the effect of lowering the process load. In detail a first plurality of sound features is received in a buffer (330), and a second plurality of sound features is received in the buffer 330). While receiving each of the second plurality of sound features in the buffer, a first number of the sound features are processed from the buffer. The first number of the sound features includes two or more sound features. Further, the method includes determining a keyword score (360) for each of the processed sound features and detecting the input sound as the target keyword (370) if at least one of the keyword scores is greater than a threshold score.

Abstract translation: 公开了一种从用于激活移动设备中的功能的输入声音中检测目标关键字的方法。 在该方法中，从输入流中提取声音特征，并且生成包括特定声音特征的平均值和方差的统计信息（340）。 基于统计，当当前值与先前值之间的差异不显着时，该方法自适应地跳过声音特征的归一化，这具有降低处理负载的效果。 详细地，在缓冲器（330）中接收第一多个声音特征，并且在缓冲器330中接收第二多个声音特征。 在接收缓冲器中的第二多个声音特征中的每一个时，从缓冲器处理第一数量的声音特征。 第一个声音特征包括两个或多个声音特征。 此外，该方法包括：如果关键词分数中的至少一个大于阈值分数，则确定每个已处理声音特征的关键词分数（360）并检测输入声音作为目标关键词（370）。