公开(公告)号：WO2015160586A1

公开(公告)日：2015-10-22

申请号：PCT/US2015/024873

申请日：2015-04-08

Applicant: QUALCOMM INCORPORATED

Inventor： YUN, Sungrack ,  KIM, Taesu

IPC: G10L15/07 ,  G10L15/08 ,  G10L15/22

CPC classification number: G10L15/02 ,  G10L15/07 ,  G10L2015/027 ,  G10L2015/088 ,  G10L2015/226

Abstract: According to an aspect of the present disclosure, a method for generating a keyword model of a user-defined keyword in an electronic device is disclosed. The method includes receiving at least one input indicative of the user-defined keyword, determining a sequence of subwords from the at least one input, generating the keyword model associated with the user-defined keyword based on the sequence of subwords and a subword model of the subwords, wherein the subword model is configured to model a plurality of acoustic features of the subwords based on a speech database, and providing the keyword model associated with the user-defined keyword to a voice activation unit configured with a keyword model associated with a predetermined keyword.

Abstract translation: 根据本公开的一个方面，公开了一种用于在电子设备中生成用户定义的关键字的关键字模型的方法。 该方法包括接收指示用户定义的关键字的至少一个输入，从至少一个输入确定子词序列，基于子词序列生成与用户定义关键词相关联的关键字模型，以及子词模型 所述子词，其中所述子词模型被配置为基于语音数据库对所述子词的多个声学特征建模，以及将与所述用户定义的关键字相关联的关键词模型提供给配置有与所述关键字模型相关联的关键词模型的语音激活单元 预定关键词

公开(公告)号：WO2015160519A1

公开(公告)日：2015-10-22

申请号：PCT/US2015/023935

申请日：2015-04-01

Applicant: QUALCOMM INCORPORATED

Inventor： KIM, Taesu ,  JIN, Minho ,  CHO, Juncheol

IPC: G10L15/22 ,  G10L17/22 ,  G10L17/24 ,  G10L15/08

CPC classification number: G10L17/22 ,  G10L15/22 ,  G10L17/24 ,  G10L25/48 ,  G10L2015/088 ,  G10L2015/223 ,  H04M1/72519 ,  H04M2250/74

Abstract: A method for performing a function in an electronic device is disclosed. The method may include receiving an input sound stream including a speech command indicative of the function and identifying the function from the speech command in the input sound stream. Further, the method may determine a security level associated with the speech command. It may be verified whether the input sound stream is indicative of a user authorized to perform the function based on the security level. In response to verifying that the input sound stream is indicative of the user, the function may be performed.

Abstract translation: 公开了一种在电子设备中执行功能的方法。 该方法可以包括接收包括指示功能的语音命令的输入声音流，并且从输入声音流中的语音命令中识别功能。 此外，该方法可以确定与语音命令相关联的安全级别。 可以验证输入声音流是否指示基于安全级别被授权执行功能的用户。 响应于验证输入声音流是否表示用户，可以执行该功能。

公开(公告)号：WO2015105893A1

公开(公告)日：2015-07-16

申请号：PCT/US2015/010504

申请日：2015-01-07

Applicant: QUALCOMM INCORPORATED

Inventor： KIM, Taesu ,  LEE, Minsub ,  CHO, Jun-Cheol

IPC: H04H60/37 ,  H04H60/58

CPC classification number: G06F3/165 ,  H04H60/37 ,  H04H60/58 ,  H04L67/10

Abstract: A method, performed in an electronic device, for tracking a piece of music in an audio stream is disclosed. The method may receive a first portion of the audio stream and extract a first sound feature based on the first portion of the audio stream. Also, the method may determine whether the first portion of the audio stream is indicative of music based on the first sound feature. In response to determining that the first portion of the audio stream is indicative of music, a piece of music may be identified based on the first portion of the audio stream. Further, upon receiving a second portion of the audio stream, the method may extract a second sound feature based on the second portion of the audio stream and determine whether the second portion of the audio stream is indicative of the first piece of music.

Abstract translation: 公开了一种在电子设备中执行的用于跟踪音频流中的一段音乐的方法。 该方法可以接收音频流的第一部分，并且基于音频流的第一部分提取第一声音特征。 此外，该方法可以基于第一声音特征来确定音频流的第一部分是否指示音乐。 响应于确定音频流的第一部分指示音乐，可以基于音频流的第一部分来识别音乐片段。 此外，在接收到音频流的第二部分时，该方法可以基于音频流的第二部分提取第二声音特征，并且确定音频流的第二部分是否指示第一音乐。

公开(公告)号：WO2015084927A1

公开(公告)日：2015-06-11

申请号：PCT/US2014/068307

申请日：2014-12-03

Applicant: QUALCOMM INCORPORATED

Inventor： YUN, Sungrack ,  KIM, Taesu ,  JIN, Minho

IPC: G06F3/01 ,  G06F3/038

CPC classification number: G06F3/013 ,  G06F3/012 ,  G06F3/038 ,  G06K9/00288

Abstract: A method, performed by a connection manager, for connecting an input device and one of a plurality of electronic devices as a target device is disclosed. The method includes detecting a face of a user in a captured image, and determining a first gaze direction of the user from the face of the user in the captured image. Based on the first gaze direction, the method determines the target device in the plurality of electronic devices and connects the input device and the target device.

Abstract translation: 公开了一种由连接管理器执行的用于连接输入设备和作为目标设备的多个电子设备中的一个的方法。 所述方法包括：在拍摄图像中检测用户的脸部，以及从拍摄图像中的用户的脸部确定用户的第一注视方向。 基于第一注视方向，该方法确定多个电子设备中的目标设备并连接输入设备和目标设备。

公开(公告)号：WO2015041946A1

公开(公告)日：2015-03-26

申请号：PCT/US2014/055402

申请日：2014-09-12

Applicant: QUALCOMM INCORPORATED

Inventor： PARK, Min-Kyu ,  KIM, Taesu ,  YUN, Sungrack ,  HWANG, Kyu Woong ,  CHO, Jun-Cheol

IPC: H04L29/06 ,  H04W12/08

CPC classification number: H04L63/0853 ,  H04L63/0815 ,  H04L63/105 ,  H04L63/107 ,  H04W12/08

Abstract: According to an aspect of the present disclosure, a method for controlling access to a plurality of electronic devices is disclosed. The method includes detecting whether a first device is in contact with a user, adjusting a security level of the first device to activate the first device when the first device is in contact with the user, detecting at least one second device within a communication range of the first device, and adjusting a security level of the at least one second device to control access to the at least one second device based on a distance between the first device and the at least one second device.

Abstract translation: 根据本公开的一个方面，公开了一种用于控制对多个电子设备的访问的方法。 该方法包括检测第一设备是否与用户接触，当第一设备与用户接触时调整第一设备的安全级别以激活第一设备，检测在第一设备的通信范围内的至少一个第二设备 并且基于所述第一设备和所述至少一个第二设备之间的距离来调整所述至少一个第二设备的安全级别以控制对所述至少一个第二设备的访问。

公开(公告)号：WO2014179334A1

公开(公告)日：2014-11-06

申请号：PCT/US2014/035906

申请日：2014-04-29

Applicant: QUALCOMM INCORPORATED

Inventor： KIM, Taesu ,  CHANDHOK, Ravinder Paul ,  LEE, Te-Won

IPC: H04W4/04 ,  H04W12/06 ,  H04W76/02

CPC classification number: H04W12/06 ,  G06Q30/0261 ,  H04L63/061 ,  H04W4/043 ,  H04W12/04 ,  H04W76/14

Abstract: In an embodiment, two or more local wireless peer-to-peer connected user equipments (UEs) capture local ambient sound, and report information associated with the captured local ambient sound to an authentication device. The authentication device compares the reported information to determine a degree of environmental similarity for the UEs, and selectively authenticates the UEs as being in a shared environment based on the determined degree of environmental similarity. A given UE among the two or more UEs selects a target UE for performing a given action based on whether the authentication device authenticates the UEs as being in the shared environment.

Abstract translation: 在一个实施例中，两个或多个本地无线对等连接的用户设备（UE）捕获本地环境声音，并将与所捕获的本地环境声音相关联的信息报告给认证设备。 认证装置比较报告的信息以确定UE的环境相似度，并且基于所确定的环境相似度来选择性地将UE认证为处于共享环境中。 两个或多个UE中的给定UE基于认证设备将UE认证为在共享环境中来选择目标UE执行给定动作。

公开(公告)号：WO2017095560A1

公开(公告)日：2017-06-08

申请号：PCT/US2016/058920

申请日：2016-10-26

Applicant: QUALCOMM INCORPORATED

Inventor： YUN, Sungrack ,  KIM, Taesu ,  KIM, Sungwoong ,  KIM, Heeman

IPC: G10L15/22 ,  H04M1/27 ,  H04M1/725 ,  G06F3/16

CPC classification number: G06F21/32 ,  G06F3/167 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/228 ,  H04M1/67 ,  H04M1/72569

Abstract: A method for generating a notification by an electronic device to alert a user of the electronic device is disclosed. In this method, a speech phrase may be received. Then, the received speech phrase may be recognized, by a processor, as a command to generate the notification. In addition, one or more context data of the electronic device may be detected by at least one sensor. It may be determined whether the notification is to be generated at least based on the context data. The notification may be generated, by the processor, based on the context data and the command to generate the notification.

Abstract translation: 公开了一种用于由电子设备生成通知以提醒电子设备的用户的方法。 在这种方法中，可以接收一个语音短语。 然后，处理器可以将接收到的语音短语识别为生成通知的命令。 另外，电子设备的一个或多个情境数据可以由至少一个传感器检测。 可以确定是否至少基于上下文数据来生成通知。 通知可以由处理器基于上下文数据和用于生成通知的命令来生成。

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：WO2015038435A1

公开(公告)日：2015-03-19

申请号：PCT/US2014/054352

申请日：2014-09-05

Applicant: QUALCOMM INCORPORATED

Inventor： YUN, Sungrack ,  KIM, Taesu ,  CHO, Jun-Cheol ,  PARK, Min-Kyu ,  HWANG, Kyu Woong

IPC: H04L29/06 ,  G06F21/32

CPC classification number: G10L17/20 ,  G06F21/32 ,  G10L17/005 ,  G10L17/04 ,  G10L17/24 ,  G10L17/26 ,  H04L63/0861 ,  H04L63/105

Abstract: According to an aspect of the present disclosure, a method for controlling access to a plurality of applications in an electronic device is disclosed. The method includes receiving a voice command from a speaker for accessing a target application among the plurality of applications, and verifying whether the voice command is indicative of a user authorized to access the applications based on a speaker model of the authorized user. In this method, each application is associated with a security level having a threshold value. The method further includes updating the speaker model with the voice command if the voice command is verified to be indicative of the user, and adjusting at least one of the threshold values based on the updated speaker model.

Abstract translation: 根据本公开的一个方面，公开了一种用于控制对电子设备中的多个应用的​​访问的方法。 该方法包括从扬声器接收用于访问多个应用中的目标应用的语音命令，以及基于授权用户的说话者模型来验证语音命令是否指示被授权访问应用的用户。 在该方法中，每个应用与具有阈值的安全级别相关联。 该方法还包括如果语音命令被验证为指示用户，则利用语音命令更新说话者模型，并且基于更新的说话者模型来调整至少一个阈值。

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。