公开(公告)号：US09390719B1

公开(公告)日：2016-07-12

申请号：US13648108

申请日：2012-10-09

Applicant: Dominik Roblek ,  Matthew Sharifi

Inventor： Dominik Roblek ,  Matthew Sharifi

IPC: G06F17/00 ,  G10L19/022 ,  G06F17/30 ,  G10L19/025 ,  G10L19/26

CPC classification number: G10L19/022 ,  G06F17/30743 ,  G10L19/025 ,  G10L19/26 ,  G10L25/51 ,  G10L25/60

Abstract: Systems and methods are provided herein relating to audio matching. The density and quality of interest points can be controlled to assure a small but uniform number of high quality interest points. By scoring interest points based on quality and comparing them over time, those interest points that maintain a high quality when compared with a varying number of neighboring interest points can be retained, while those interest points that do not maintain a high quality can be discarded. Thus, the scalability of an audio matching system can be improved while retaining accuracy.

Abstract translation: 本文提供了与音频匹配有关的系统和方法。 可以控制兴趣点的密度和质量，以确保高质量的兴趣点数量小而均匀。 通过根据质量对利益点进行评分并对其进行比较，可以保留与不同数量的邻近兴趣点相比保持高质量的兴趣点，而不能保持高质量的兴趣点可以被​​丢弃。 因此，可以在保持精度的同时提高音频匹配系统的可扩展性。

公开(公告)号：US09202472B1

公开(公告)日：2015-12-01

申请号：US13434832

申请日：2012-03-29

Applicant: Matthew Sharifi ,  Dominik Roblek ,  George Tzanetakis

Inventor： Matthew Sharifi ,  Dominik Roblek ,  George Tzanetakis

IPC: G06F17/30 ,  G10L19/018

CPC classification number: G10L19/018 ,  G10L25/03

Abstract: Systems and methods for generating unique pitch-resistant descriptors for audio clips are provided. In one or more embodiments, a descriptor for an audio clip is generated as a function of relative magnitudes between interest points within the audio clip's time-frequency representation. A number of techniques for leveraging the relative magnitudes to generate descriptors are considered. These techniques include ordering of interest points as a function of ascending or descending magnitude, creation of binary vectors based on magnitude comparisons between pairs of points, and calculation of quantized magnitude ratios between pairs of points. Descriptors generated based on relative magnitudes according to the techniques disclosed herein are relatively invariant to common transformations to the original audio clip, such as pitch shifting, time stretching, global volume changes, equalization, and/or dynamic range compression.

Abstract translation: 提供了用于为音频剪辑生成独特的音高描述符的系统和方法。 在一个或多个实施例中，音频剪辑的描述符作为音频剪辑的时间 - 频率表示内的兴趣点之间的相对幅度的函数被生成。 考虑了利用相对幅度来生成描述符的许多技术。 这些技术包括将兴趣点排序为上升或下降幅度的函数，基于点对之间的幅度比较的二进制向量的创建以及点对之间的量化幅度比的计算。 基于根据本文公开的技术的相对幅度生成的描述符对于原始音频剪辑的常见变换（例如音调偏移，时间延伸，全局音量变化，均衡和/或动态范围压缩）是相对不变的。

公开(公告)号：US08886543B1

公开(公告)日：2014-11-11

申请号：US13296899

申请日：2011-11-15

Applicant: Matthew Sharifi ,  George Tzanetakis ,  Annie Chen ,  Dominik Roblek

Inventor： Matthew Sharifi ,  George Tzanetakis ,  Annie Chen ,  Dominik Roblek

IPC: G10L11/00

CPC classification number: G10L19/018

Abstract: System and methods for characterizing interest points within a fingerprint are disclosed herein. The systems include generating a set of interest points and an anchor point related to an audio sample. A quantized absolute frequency of an anchor point can be calculated and used to calculate a set of quantized ratios. A fingerprint can then be generated based upon the set of quantized ratios and used in comparison to reference fingerprints to identify the audio sample. The disclosed systems and methods provide for an audio matching system robust to pitch-shift distortion by using quantized ratios within fingerprints rather than solely using absolute frequencies of interest points. Thus, the disclosed system and methods result in more accurate audio identification.

Abstract translation: 本文公开了用于表征指纹内的兴趣点的系统和方法。 系统包括产生一组感兴趣点和与音频样本相关的定位点。 锚定点的量化绝对频率可以被计算并用于计算一组量化比率。 然后可以基于所述量化比率的集合生成指纹，并且与参考指纹进行比较以用于识别音频样本。 所公开的系统和方法通过使用指纹内的量化比率而不是仅使用感兴趣点的绝对频率来提供对音调偏移失真鲁棒的音频匹配系统。 因此，所公开的系统和方法导致更准确的音频识别。

公开(公告)号：US08868223B1

公开(公告)日：2014-10-21

申请号：US13553735

申请日：2012-07-19

Applicant: Matthew Sharifi

Inventor： Matthew Sharifi

IPC: G06F17/00

CPC classification number: G01S5/24 ,  G06F17/30743 ,  G10L25/48

Abstract: Systems and methods for determining location based on audio fingerprinting are disclosed. An extraction component extracts a set of interest points from an audio signal associated with an audio announcement. Then a matching component determines if the extracted set of interest points matches a set of interest points representative of an audio fingerprint in a data store comprising audio fingerprints. In an aspect, the audio fingerprints in the audio fingerprint data store represent announcements for underground transportation systems. A location component further determines location information associated with the audio fingerprint based in part on the set of extracted interest points matching the set of audio interest points representative of the audio fingerprint in the data store.

Abstract translation: 公开了基于音频指纹识别位置的系统和方法。 提取组件从与音频通知相关联的音频信号中提取一组感兴趣点。 然后，匹配组件确定所提取的感兴趣组是否与包括音频指纹的数据存储器中的表示音频指纹的一组感兴趣点匹配。 在一方面，音频指纹数据存储器中的音频指纹代表地下运输系统的公告。 位置组件还部分地基于与代表数据存储器中的音频指纹的音频兴趣点集合匹配的提取的兴趣点集合来确定与音频指纹相关联的位置信息。

公开(公告)号：US08863182B1

公开(公告)日：2014-10-14

申请号：US13399759

申请日：2012-02-17

Applicant: Matthew Sharifi ,  Graeme Rimmer

Inventor： Matthew Sharifi ,  Graeme Rimmer

IPC: H04N7/10 ,  H04N7/025

CPC classification number: H04N21/8456 ,  H04L65/4084 ,  H04L65/605 ,  H04N21/233 ,  H04N21/23424 ,  H04N21/2387 ,  H04N21/812

Abstract: Systems and methods are provided herein relating to video editing and more particularly to stitching an insert video within a target video without transcoding. Through dynamically stitching a video, such as an advertisement, within a video, a content provider can transmit a stitched video instead of separate content videos and advertisement videos that a local uncontrolled video player would be responsible for combining and playing. Systems and methods herein provide for receiving a target video and an insert video and dynamically stitching the insert video within the target video to create a stitched video. The stitched video can then be transmitted that plays both the target video and the insert video within the target video, irrespective of the player on which a user views the stitched video.

Abstract translation: 本文提供了与视频编辑有关的系统和方法，并且更具体地涉及将目标视频中的插入视频拼接而不进行代码转换。 通过在视频内动态地拼接诸如广告的视频，内容提供商可以发送缝合的视频，而不是单独的内容视频和本地不受控制的视频播放器负责组合和播放的广告视频。 这里的系统和方法提供了接收目标视频和插入视频，并且在目标视频内动态拼接插入视频以创建缝合视频。 然后可以发送拼接的视频，其同时在目标视频内同时播放目标视频和插入视频，而与用户观看拼接视频的播放器无关。

公开(公告)号：US08805683B1

公开(公告)日：2014-08-12

申请号：US13404978

申请日：2012-02-24

Applicant: Matthew Wiseman ,  Yaniv Bernstein ,  Daniel Switkin ,  Gheorghe M. Postelnicu ,  Matthew Sharifi ,  Annie Chen ,  Dominik Roblek

Inventor： Matthew Wiseman ,  Yaniv Bernstein ,  Daniel Switkin ,  Gheorghe M. Postelnicu ,  Matthew Sharifi ,  Annie Chen ,  Dominik Roblek

IPC: G10L15/00

CPC classification number: G10L15/22 ,  G06F17/30758 ,  G10L15/30 ,  G10L25/54

Abstract: An audio recognition service recognizes an audio sample across multiple content types. At least a partial set of results generated by the service are returned to a client while the audio sample is still being recorded and/or transmitted. The client additionally displays the results in real-time or near real-time to the user. The audio sample can be sent over a first HTTP connection and the results can be returned over a second HTTP connection. The audio recognition service further processes check-in selections received from the client for content items indicated by the results. Responsive to receiving the check-in selections, the service determines whether a user is eligible for a reward. If the user is eligible, the service provides the reward.

Abstract translation: 音频识别服务识别多种内容类型的音频样本。 当音频样本仍然被记录和/或发送时，由服务产生的至少一部分结果返回给客户机。 客户端另外向用户实时或接近实时显示结果。 音频样本可以通过第一个HTTP连接发送，并且可以通过第二个HTTP连接返回结果。 音频识别服务进一步处理从客户端接收的用于由结果指示的内容项的登记选择。 响应于接收签入选择，该服务确定用户是否有资格获得奖励。 如果用户符合条件，则该服务将提供奖励。

公开(公告)号：US20130235027A1

公开(公告)日：2013-09-12

申请号：US13417598

申请日：2012-03-12

Applicant: Matthew Sharifi ,  Annie Chen ,  Dominik Roblek

Inventor： Matthew Sharifi ,  Annie Chen ,  Dominik Roblek

IPC: G06F17/00

CPC classification number: G06F17/30241 ,  G06F17/3053 ,  G06F17/30817 ,  G06F17/30867 ,  G06F17/3087 ,  G06Q10/0637 ,  G09B29/006 ,  G09B29/007

Abstract: This disclosure relates to dynamic display of content consumption by geographic location. A recognition component recognizes content being consumed by a set of users, and identifies geographic locations of the consumption and a set of characteristics associated with the consumption. An aggregation component ranks the consumed content based on a subset of the characteristics associated with the consumption, and a display component generates a map displaying subsets of the consumed content as a function of respective rankings and geographic location.

Abstract translation: 本公开涉及通过地理位置动态显示内容消费。 识别组件识别由一组用户消费的内容，并且识别消费的地理位置和与消费相关联的一组特征。 聚合组件基于与消费相关联的特征的子集来排列消耗的内容，并且显示组件生成显示作为相应排名和地理位置的函数的消费内容的子集的映射。

公开(公告)号：US08488943B1

公开(公告)日：2013-07-16

申请号：US13362725

申请日：2012-01-31

Applicant: Matthew Sharifi

Inventor： Matthew Sharifi

IPC: G11B27/34 ,  H04N5/76

CPC classification number: H04N9/87 ,  G11B27/034 ,  H04N5/76 ,  H04N5/91 ,  H04N9/8211

Abstract: Systems and methods for editing an MP4 multimedia container without transcoding are disclosed herein. Editing operations can be accomplished by transforming data included in the multimedia container rather than by transforming raw data streams and then reconverting to MP4 (or another) file format. In response to a target range that identifies a portion of the media content to maintain, a corresponding sample range in terms of the MP4 format can be constructed and data outside that range can be discarded, e.g., from the mdat atom and the sample tables atom(s).

Abstract translation: 本文公开了用于编辑没有代码转换的MP4多媒体容器的系统和方法。 编辑操作可以通过转换包含在多媒体容器中的数据来实现，而不是通过转换原始数据流，然后重新转换为MP4（或另一种）文件格式。 响应于识别要维护的媒体内容的一部分的目标范围，可以构建关于MP4格式的对应样本范围，并且可以丢弃该范围之外的数据，例如，从mdat原子和样本表原子 （s）。

公开(公告)号：US20090187954A1

公开(公告)日：2009-07-23

申请号：US12011205

申请日：2008-01-23

Applicant: Andreas Tuerk ,  Stephen Spence ,  Natalie Doduc ,  Karen Groenink ,  Matthew Sharifi ,  Tim Jones ,  Dwipal Desai

Inventor： Andreas Tuerk ,  Stephen Spence ,  Natalie Doduc ,  Karen Groenink ,  Matthew Sharifi ,  Tim Jones ,  Dwipal Desai

IPC: H04N7/173

CPC classification number: H04N21/482 ,  H04N5/44513 ,  H04N5/44591 ,  H04N21/41407 ,  H04N21/422 ,  H04N21/443 ,  H04N21/485

Abstract: The described embodiments of the present invention provide a video database client application configured to execute on a wireless communication device or a device with a small display screen. The video database client application includes a user interface including user interface components designed to access video information and view videos using the wireless communication device. The video database client application includes a video player module to integrate and control a native video player within the user interface. The video database client application further includes a video database interface module adapted to retrieve videos and video information from the video database. The video database interface module functions to pre-fetch information from the video database based on anticipated user information needs.

Abstract translation: 本发明的所描述的实施例提供一种被配置为在具有小显示屏的无线通信设备或设备上执行的视频数据库客户端应用。 视频数据库客户端应用程序包括用户界面，其包括设计用于访问视频信息的用户界面组件，以及使用无线通信设备查看视频。 视频数据库客户端应用程序包括视频播放器模块，用于在用户界面内整合和控制本地视频播放器。 视频数据库客户端应用还包括适于从视频数据库检索视频和视频信息的视频数据库接口模块。 视频数据库接口模块用于根据预期的用户信息需要从视频数据库预取信息。

公开(公告)号：US09384734B1

公开(公告)日：2016-07-05

申请号：US13404971

申请日：2012-02-24

Applicant: Matthew Wiseman ,  Gheorghe M. Postelnicu ,  Dominik Roblek ,  Yaniv Bernstein ,  Matthew Sharifi ,  Annie Chen

Inventor： Matthew Wiseman ,  Gheorghe M. Postelnicu ,  Dominik Roblek ,  Yaniv Bernstein ,  Matthew Sharifi ,  Annie Chen

IPC: G10L15/26

CPC classification number: G10L15/26 ,  G06F17/3074 ,  G06F17/30743 ,  G06F17/30766 ,  G06F17/30769 ,  G10H1/0008 ,  G10H1/0033 ,  G10H2240/141 ,  G10L15/00 ,  G10L15/265 ,  G10L17/00 ,  G10L25/51

Abstract: An audio recognition service recognizes an audio sample across multiple content types. At least a partial set of results generated by the service are returned to a client while the audio sample is still being recorded and/or transmitted. The client additionally displays the results in real-time or near real-time to the user. The audio sample can be sent over a first HTTP connection and the results can be returned over a second HTTP connection. The audio recognition service further processes check-in selections received from the client for content items indicated by the results. Responsive to receiving the check-in selections, the service determines whether a user is eligible for a reward. If the user is eligible, the service provides the reward.

Abstract translation: 音频识别服务识别多种内容类型的音频样本。 当音频样本仍然被记录和/或发送时，由服务产生的至少一部分结果返回给客户机。 客户端另外向用户实时或接近实时显示结果。 音频样本可以通过第一个HTTP连接发送，并且可以通过第二个HTTP连接返回结果。 音频识别服务进一步处理从客户端接收的用于由结果指示的内容项的登记选择。 响应于接收签入选择，该服务确定用户是否有资格获得奖励。 如果用户符合条件，则该服务将提供奖励。