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：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：WO2015161240A2

公开(公告)日：2015-10-22

申请号：PCT/US2015/026453

申请日：2015-04-17

Applicant: QUALCOMM INCORPORATED

Inventor： VISSER, Erik ,  KIM, Lae-Hoon ,  JIN, Minho ,  GUO, Yinyi

IPC: G10L17/04

CPC classification number: G06F3/167 ,  G10L15/22 ,  G10L17/04 ,  G10L17/08 ,  G10L17/22

Abstract: A device includes a memory, a receiver, a processor, and a display. The memory is configured to store a speaker model. The receiver is configured to receive an input audio signal. The processor is configured to determine a first confidence level associated with a first portion of the input audio signal based on the speaker model. The processor is also configured to determine a second confidence level associated with a second portion of the input audio signal based on the speaker model. The display is configured to present a graphical user interface associated with the first confidence level or associated with the second confidence level.

Abstract translation: 设备包括存储器，接收器，处理器和显示器。 存储器被配置为存储扬声器模型。 接收器被配置为接收输入音频信号。 处理器被配置为基于说话者模型来确定与输入音频信号的第一部分相关联的第一置信水平。 处理器还被配置为基于说话者模型来确定与输入音频信号的第二部分相关联的第二置信度。 显示器被配置为呈现与第一置信水平相关联或与第二置信水平相关联的图形用户界面。

公开(公告)号：WO2015041915A1

公开(公告)日：2015-03-26

申请号：PCT/US2014/055104

申请日：2014-09-11

Applicant: QUALCOMM INCORPORATED

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

IPC: H04N21/466 ,  H04N21/258 ,  H04N21/234 ,  H04N21/44 ,  H04N21/439 ,  H04N21/233 ,  H04N21/431 ,  H04N21/482 ,  H04N21/442

CPC classification number: H04N21/251 ,  H04N21/233 ,  H04N21/23418 ,  H04N21/25891 ,  H04N21/26603 ,  H04N21/4316 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/4415 ,  H04N21/44218 ,  H04N21/4532 ,  H04N21/4668 ,  H04N21/4826

Abstract: A method of providing a channel program recommendation in real-time for a display device is disclosed. The method includes receiving a plurality of multimedia signal streams for a plurality of channel programs, and generating in real-time at least one video and audio content tag based on at least one of video and audio contents from the multimedia signal streams. The display device generates the channel program recommendation including at least one of the channel programs based on the at least one video and audio content tag and at least one of a plurality of viewing criteria. A notification of the channel program recommendation is then output.

Abstract translation: 公开了一种为显示设备实时提供频道节目推荐的方法。 该方法包括：接收用于多个频道节目的多个多媒体信号流，并且基于来自多媒体信号流的视频和音频内容中的至少一个，实时生成至少一个视频和音频内容标签。 显示设备基于至少一个视频和音频内容标签以及多个观看标准中的至少一个，生成包括至少一个频道节目的频道节目推荐。 然后输出通道节目推荐的通知。

公开(公告)号：WO2017160453A1

公开(公告)日：2017-09-21

申请号：PCT/US2017/017991

申请日：2017-02-15

Applicant: QUALCOMM INCORPORATED

Inventor： VISSER, Erik ,  JIN, Minho ,  KIM, Lae-Hoon ,  PERI, Raghuveer ,  ZHANG, Shuhua

IPC: G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06N3/0454

Abstract: A method of training a device specific cloud-based audio processor includes receiving sensor data captured from multiple sensors at a local device. The method also includes receiving spatial information labels computed on the local device using local configuration information. The spatial information labels are associated with the captured sensor data. Lower layers of a first neural network are trained based on the spatial information labels and sensor data. The trained lower layers are incorporated into a second, larger neural network for audio classification. The second, larger neural network may be retrained using the trained lower layers of the first neural network.

Abstract translation: 训练设备特定的基于云的音频处理器的方法包括接收从本地设备处的多个传感器捕获的传感器数据。 该方法还包括使用本地配置信息接收在本地设备上计算的空间信息标签。 空间信息标签与捕获的传感器数据相关联。 基于空间信息标签和传感器数据来训练第一神经网络的较低层。 经训练的较低层被并入用于音频分类的第二个较大的神经网络。 第二个较大的神经网络可以使用第一个神经网络的训练后的下层重新训练。

公开(公告)号：WO2016039954A1

公开(公告)日：2016-03-17

申请号：PCT/US2015/045833

申请日：2015-08-19

Applicant: QUALCOMM INCORPORATED

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

IPC: H04N5/58 ,  G09G3/34

CPC classification number: G06F3/005 ,  G09G3/001 ,  G09G2320/0626 ,  G09G2320/066 ,  G09G2320/0666 ,  G09G2354/00 ,  G09G2360/144 ,  G09G2360/145 ,  H04N5/58 ,  H04N21/4126 ,  H04N21/42202 ,  H04N21/42222 ,  H04N21/4223 ,  H04N21/4318 ,  H04N21/44218 ,  H04N21/44222 ,  H04N21/4532 ,  H04N21/4667 ,  H04N21/4854

Abstract: A method, performed in a control device, for adjusting a display device in communication with the control device is disclosed. The method may include receiving an image of a scene including the display device from an image sensor configured with a field of view overlapping at least a portion of view of a user. A display condition of the display device may be detected from the image. The control device may determine context information associated with the user from the image. Based on the display condition and the context information associated with the user, an output display condition of the display device may be determined. A control signal for adjusting the display device may then be generated based on the output display condition.

Abstract translation: 公开了一种在控制装置中执行的用于调节与控制装置通信的显示装置的方法。 该方法可以包括从配置有与用户的至少一部分视图重叠的视场的图像传感器接收包括显示设备的场景的图像。 可以从图像检测显示装置的显示状态。 控制装置可以从图像确定与用户相关联的上下文信息。 基于与用户相关联的显示条件和上下文信息，可以确定显示设备的输出显示状态。 然后可以基于输出显示条件来生成用于调整显示装置的控制信号。

公开(公告)号：WO2015041872A1

公开(公告)日：2015-03-26

申请号：PCT/US2014/054312

申请日：2014-09-05

Applicant: QUALCOMM INCORPORATED

Inventor： YUN, Sungrack ,  HWANG, Kyu Woong ,  CHO, Jun-Cheol ,  KIM, Taesu ,  JIN, Minho ,  CHO, Yongwoo ,  KIM, Kang

IPC: H04W4/02 ,  G06F1/16 ,  G06F17/30 ,  G06T7/00 ,  G06K9/00 ,  G06F3/01

CPC classification number: G06K9/6201 ,  G06F3/012 ,  G06F17/30047 ,  G06F17/30241 ,  G06F17/30247 ,  G06F17/30265 ,  G06F17/3087 ,  G06K9/00 ,  G06K9/00671 ,  H04W4/02

Abstract: A method for providing object information for a scene in a wearable computer is disclosed. In this method, an image of the scene is captured. Further, the method includes determining a current location of the wearable computer and a view direction of an image sensor of the wearable computer and extracting at least one feature from the image indicative of at least one object. Based on the current location, the view direction, and the at least one feature, information on the at least one object is determined. Then, the determined information is output.

Abstract translation: 公开了一种用于在可穿戴式计算机中提供场景的对象信息的方法。 在该方法中，捕获场景的图像。 此外，该方法包括确定可穿戴计算机的当前位置和可穿戴计算机的图像传感器的视图方向，并从指示至少一个对象的图像中提取至少一个特征。 基于当前位置，视图方向和至少一个特征，确定关于至少一个对象的信息。 然后，输出确定的信息。

公开(公告)号：WO2014182460A2

公开(公告)日：2014-11-13

申请号：PCT/US2014/035247

申请日：2014-04-24

Applicant: QUALCOMM INCORPORATED

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

IPC: G10L15/22

CPC classification number: G06F3/167 ,  G10L15/08 ,  G10L15/142 ,  G10L15/22

Abstract: A method of detecting a target keyword for activating a function in an electronic device is disclosed. The method includes receiving an input sound starting from one of the plurality of portions of the target keyword. The input sound may be periodically received based on a duty cycle. The method extracts a plurality of sound features from the input sound, and obtains state information on a plurality of states associated with the portions of the target keyword. Based on the extracted sound features and the state information, the input sound may be detected as the target keyword. The plurality of states includes a predetermined number of entry states indicative of a predetermined number of the plurality of portions.

Abstract translation: 公开了一种检测用于激活电子设备中的功能的目标关键字的方法。 该方法包括从目标关键词的多个部分中的一个开始接收输入声音。 可以基于占空比周期性地接收输入声音。 该方法从输入声音中提取多个声音特征，并且获得关于与目标关键词的部分相关联的多个状态的状态信息。 基于提取的声音特征和状态信息，可以检测输入声音作为目标关键字。 多个状态包括指示多个部分中预定数量的预定数量的进入状态。

公开(公告)号：WO2014137384A1

公开(公告)日：2014-09-12

申请号：PCT/US2013/057386

申请日：2013-08-29

Applicant: QUALCOMM INCORPORATED

Inventor： CHO, Yongwoo ,  KIM, Taesu ,  JIN, Minho ,  HWANG, Kyu Woong

IPC: H04W4/22

CPC classification number: G08B25/10 ,  H04W4/90

Abstract: A method includes receiving an alarm sound including information related to an emergency event. The method also includes transmitting, to a server, identification information of the mobile device and the information. The method further includes receiving, from the server, an instruction for responding to the emergency event. The method further includes outputting the instruction.

Abstract translation: 一种方法包括接收包括与紧急事件相关的信息的警报声音。 该方法还包括向服务器发送移动设备的标识信息和信息。 该方法还包括从服务器接收响应紧急事件的指令。 该方法还包括输出指令。

公开(公告)号：WO2013141986A1

公开(公告)日：2013-09-26

申请号：PCT/US2013/026324

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

CPC classification number: H04W52/0225 ,  G06F1/1684 ,  G06F1/3215 ,  G06F1/3231 ,  G06F1/329 ,  H02J9/005 ,  H04M1/72569 ,  H04W4/04 ,  Y02D10/173 ,  Y02D10/24 ,  Y02D70/00 ,  Y02D70/1222 ,  Y02D70/1262 ,  Y02D70/1264 ,  Y02D70/164

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，以及基于与所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的上下文组的服务器，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。