公开(公告)号：US09275427B1

公开(公告)日：2016-03-01

申请号：US14019086

申请日：2013-09-05

Applicant: Google Inc.

Inventor： Matthew Sharifi

IPC: G06T1/00

CPC classification number: G06T1/0021 ,  G06F17/30784 ,  G06F17/30787 ,  G06F17/30799 ,  G06K9/00744

Abstract: Implementations are provided herein relating to audiovisual matching. Audio and video channel data is merged to create a single multi-channel fingerprint used to match media content. Audio channel data is used to generate audio fingerprints. Video channel data is used to generate a video fingerprints. Multi-channel fingerprints can then be generated based on the audio channel fingerprints and video channel fingerprints. In this sense, entropy can be increased while the multi-channel fingerprint can be less resistant to noise.

公开(公告)号：US20160035388A1

公开(公告)日：2016-02-04

申请号：US14884522

申请日：2015-10-15

Applicant: Google Inc.

Inventor： Matthew Sharifi

IPC: G11B27/034 ,  G11B27/19 ,  H04N19/40

CPC classification number: G11B27/034 ,  G11B27/19 ,  H04L65/605 ,  H04L65/607 ,  H04N7/14 ,  H04N7/173 ,  H04N7/17318 ,  H04N19/40 ,  H04N21/2743 ,  H04N21/41407 ,  H04N21/6375 ,  H04N21/8456

Abstract: Devices and methods are provided herein relating to video chunking for robust, progressive upload. Video can be parsed to determined byte offsets associated with prospective chunk boundaries. Chunks can be generated based on the prospective chunk boundaries and a preferred chunk size. Sample tables can be generated for each chunk. The chunks can be fully self contained, in that they can be received and transcoded independently of other chunks. Thus, if one chunk fails, only that chunk needs to be retransmitted versus the entire video.

Abstract translation: 本文提供了与视频分块相关的设备和方法，用于强大的逐行上载。 可以将视频解析为与预期块边界相关联的确定的字节偏移。 可以基于预期的块边界和优选的块大小来生成块。 可以为每个块生成示例表。 这些块可以完全自包含，因为它们可以独立于其他块被接收和转码。 因此，如果一个组块出现故障，则只需要重新发送该组块，而不需要对整个视频进行重传。

公开(公告)号：US20160027044A1

公开(公告)日：2016-01-28

申请号：US14555111

申请日：2014-11-26

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  David Petrou

IPC: G06Q30/02

CPC classification number: G06Q30/0251

Abstract: Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for providing content. Snapshots associated with use of a computing device by a user are received. Each snapshot is based on content presented to the user. The snapshots are evaluated. For each respective snapshot, a respective set of entities indicated by the respective snapshot is identified. Indications of the respective set of entities and a respective timestamp indicating a respective time that the respective snapshot was captured are associated and stored. Based on a first snapshot of the snapshots, a first time to present one or more information cards to the user is determined. At the first time, entities having a time stamp that corresponds to the first time are located. An information card is generated based on the located entities. The generated information card is provided for presentation to the user.

Abstract translation: 方法，系统和装置包括在计算机可读存储介质上编码的计算机程序，包括用于提供内容的方法。 接收与用户使用计算设备相关联的快照。 每个快照都是基于呈现给用户的内容。 快照被评估。 对于每个相应的快照，识别由相应快照指示的相应的一组实体。 相应的实体集合的指示以及指示相应快照捕获的相应时间的相应时间戳被相关联并被存储。 基于快照的第一快照，确定向用户呈现一个或多个信息卡的第一时间。 在第一时间，具有对应于第一次的时间戳的实体被定位。 基于所定位的实体生成信息卡。 生成的信息卡被提供给用户呈现。

公开(公告)号：US09189826B1

公开(公告)日：2015-11-17

申请号：US14019086

申请日：2013-09-05

Applicant: Google Inc.

Inventor： Matthew Sharifi

IPC: G06T1/00

Abstract: Implementations are provided herein relating to audiovisual matching. Audio and video channel data is merged to create a single multi-channel fingerprint used to match media content. Audio channel data is used to generate audio fingerprints. Video channel data is used to generate a video fingerprints. Multi-channel fingerprints can then be generated based on the audio channel fingerprints and video channel fingerprints. In this sense, entropy can be increased while the multi-channel fingerprint can be less resistant to noise.

公开(公告)号：US20150317281A1

公开(公告)日：2015-11-05

申请号：US14265868

申请日：2014-04-30

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  Dominik Roblek

IPC: G06F17/16 ,  G06F17/15

CPC classification number: G06F17/15 ,  G06F17/16

Abstract: A computer-implemented method includes obtaining first and second binary vectors. For each of a plurality of vector locations in a first of j words in the first binary vector, the method includes shifting the binary values for the second binary vector so that a particular one of the binary values in the second binary vector is located at a vector location in a first of the k words in the second binary vector that matches the vector location in the first of j words in the first binary vector. For each of the j words in the first binary vector, the method includes aligning the second binary vector with the word in the first binary vector and determining a binary correlation score. A similarity of the first binary vector and the second binary vector can be determined based at least on one or more of the determined binary correlation scores.

Abstract translation: 计算机实现的方法包括获得第一和第二二进制向量。 对于第一二进制向量中的j个字中的第一个中的多个向量位置中的每一个，所述方法包括移位第二二进制向量的二进制值，使得第二二进制向量中的二进制值中的特定一个位于 第二个二进制向量中的k个字中的第一个的向量位置与第一个二进制向量中的第一个j个字中的向量位置相匹配。 对于第一二进制向量中的每个j个字，所述方法包括将第二二进制向量与第一二进制向量中的单词进行对齐并确定二进制相关分数。 可以至少基于所确定的二进制相关分数中的一个或多个来确定第一二进制向量和第二二进制向量的相似性。

公开(公告)号：US09153239B1

公开(公告)日：2015-10-06

申请号：US13803686

申请日：2013-03-14

Applicant: Google Inc.

Inventor： Gheorghe Postelnicu ,  Matthew Sharifi

IPC: G10L19/018

CPC classification number: G10L25/51 ,  G10L25/18

Abstract: Identifying near identical versions of a probe sample from reference files comprises identifying discriminative regions of reference matches by generating a similarity matrix. The discriminative time frames are communicated to a client device and additional data associated with the probe sample can be retrieved having features of the discriminative regions. Based on the additional data, a single match can be generated to identify the probe sample.

Abstract translation: 识别来自参考文件的探针样本的近似相同版本包括通过生成相似性矩阵来识别参考匹配的识别区域。 鉴别时间帧被传送到客户端设备，并且可以检索与探测器样本相关联的附加数据，其具有区别区域的特征。 基于附加数据，可以生成单个匹配以识别探针样本。

公开(公告)号：US20150279374A1

公开(公告)日：2015-10-01

申请号：US14447115

申请日：2014-07-30

Applicant: Google Inc.

Inventor： Dominik Roblek ,  Matthew Sharifi

IPC: G10L17/24

CPC classification number: G10L17/24 ,  G10L15/02 ,  G10L17/04 ,  G10L2015/025

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for verifying an identity of a user. The methods, systems, and apparatus include actions of receiving a request for a verification phrase for verifying an identity of a user. Additional actions include, in response to receiving the request for the verification phrase for verifying the identity of the user, identifying subwords to be included in the verification phrase and in response to identifying the subwords to be included in the verification phrase, obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase. Further actions include providing the verification phrase as a response to the request for the verification phrase for verifying the identity of the user.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于验证用户的身份。 方法，系统和装置包括接收用于验证用户身份的验证短语的请求的动作。 附加动作包括响应于接收到用于验证用户身份的验证短语的请求，识别要包括在验证短语中的子词，并且响应于识别要包括在验证短语中的子词，获得候选短语 其包括至少一些所识别的子词作为验证短语。 进一步的操作包括提供验证短语作为对用于验证用户身份的验证短语的请求的响应。

公开(公告)号：US09123330B1

公开(公告)日：2015-09-01

申请号：US13875001

申请日：2013-05-01

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  Dominik Roblek

IPC: G10L17/00 ,  G10L15/00 ,  G10L21/00 ,  G10L25/00 ,  G06F3/00 ,  G06F3/048 ,  H04H60/32 ,  H04N7/173 ,  G10L19/018 ,  G06F17/30 ,  G06F21/16

CPC classification number: G10L17/00 ,  G06F17/30017 ,  G06F17/30026 ,  G06F17/30746 ,  G06F17/30749 ,  G06F17/30769 ,  G06F17/30864 ,  G06F21/16 ,  G10L25/51

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data encoding ambient sounds, identifying media content that matches the audio data, and a timestamp corresponding to a particular portion of the identified media content, identifying a speaker associated with the particular portion of the identified media content corresponding to the timestamp, and providing information identifying the speaker associated with the particular portion of the identified media content for output.

Abstract translation: 方法，系统和装置，包括编码在计算机存储介质上的计算机程序，用于接收编码环境声音的音频数据，识别与音频数据匹配的媒体内容以及对应于所识别的媒体内容的特定部分的时间戳， 与所标识的媒体内容的与时间戳对应的特定部分相关联的扬声器，以及提供标识与所识别的媒体内容的特定部分相关联的扬声器的信息以供输出。

公开(公告)号：US09069849B1

公开(公告)日：2015-06-30

申请号：US13648472

申请日：2012-10-10

Applicant: Google Inc.

Inventor： Dominik Roblek ,  Gheorghe Postelnicu ,  Matthew Sharifi

IPC: G06F17/00 ,  G06F17/30 ,  G10L21/04

CPC classification number: G06F17/30743 ,  G10L21/04 ,  G10L25/51

Abstract: Systems and methods are provided herein relating to speed resistant audio matching. Descriptors can be generated for a received audio signal and matched with reference descriptors. A set of hits for respective reference samples can be generated based on the matching. A histogram can then be generated that correlates probe sample hit time with reference sample hit time. In one implementation, a rolling window can be used in analyzing the histogram allowing for slight variances in the timing between probe sample hits and reference sample hits. In another implementation, the histogram generated can be based on an estimated time stretch of the probe sample. In yet another implementation, a set of histograms can be generated based on a minimum speed change, a maximum speed change, and a speed step. Histograms can be evaluated to determine a most likely matching histogram.

Abstract translation: 本文提供了与耐速度音频匹配相关的系统和方法。 可以为接收到的音频信号生成描述符，并与参考描述符匹配。 可以基于匹配来生成针对各个参考样本的一组命中。 然后可以生成将探针样品命中时间与参考样品命中时间相关联的直方图。 在一个实施方式中，可以使用滚动窗口来分析直方图，从而可以在探针样品命中和参考样品命中之间的时间上有轻微的变化。 在另一实施方案中，生成的直方图可以基于探测样本的估计时间延长。 在又一实现中，可以基于最小速度变化，最大速度变化和速度步长来生成一组直方图。 可以对直方图进行评估，以确定最可能的匹配直方图。

公开(公告)号：US09008490B1

公开(公告)日：2015-04-14

申请号：US13776017

申请日：2013-02-25

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  Dominik Roblek ,  Vera Dron ,  Ioannis Agiomyrgiannakis

IPC: H04N5/92 ,  G06F17/30

CPC classification number: G06F17/3082 ,  G06F17/30758 ,  G06F17/30787 ,  G10H1/0008 ,  G10H1/368 ,  G10H2240/075 ,  G10H2240/135 ,  G10H2240/141

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting, from among a collection of videos, a set of candidate videos that (i) are identified as being associated with a particular song, and (ii) are classified as a cappella video recordings; extracting, from each of the candidate videos of the set, a monophonic melody line from an audio channel of the candidate video; selecting, from among the set of candidate videos, a subset of the candidate videos based on a similarity of the monophonic melody line of the candidate videos of the subset with each other; and providing, to a recognizer that recognizes songs from sounds produced by a human voice, (i) an identifier of the particular song, and (ii) one or more of the monophonic melody lines of the candidate videos of the subset.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于从视频集合中选择一组候选视频，所述一组候选视频被识别为与特定歌曲相关联，以及（ii） 被列为无伴奏视频录像; 从所述候选视频的音频频道中提取来自所述组的每个候选视频的单声道旋律线; 基于所述子集的候选视频的单声道旋律线的相似度，从所述一组候选视频中选择所述候选视频的子集; 以及提供识别器，其识别由人类声音产生的声音的歌曲，（i）特定歌曲的标识符，以及（ii）该子集的候选视频的一个或多个单声道旋律线。