公开(公告)号：US20170039276A1

公开(公告)日：2017-02-09

申请号：US15298601

申请日：2016-10-20

申请人： Gracenote, Inc.

发明人： Zafar Rafii

IPC分类号： G06F17/30 ,  G10L25/45 ,  G10L25/72 ,  G10L25/21 ,  G10L25/18 ,  G10L25/54

CPC分类号： G06F17/30755 ,  G06F17/3033 ,  G06F17/30743 ,  G06F17/30778 ,  G10H2210/066 ,  G10H2240/141 ,  G10H2250/031 ,  G10L25/18 ,  G10L25/21 ,  G10L25/45 ,  G10L25/54 ,  G10L25/72

摘要： In an example context of identifying live audio, an audio processor machine accesses audio data that represents a query sound and creates a spectrogram from the audio data. Each segment of the spectrogram represents a different time slice in the query sound. For each time slice, the audio processor machine determines one or more dominant frequencies and an aggregate energy value that represents a combination of all the energy for that dominant frequency and its harmonics. The machine creates a harmonogram by representing these aggregate energy values at these dominant frequencies in each time slice. The harmonogram thus may represent the strongest harmonic components within the query sound. The machine can identify the query sound by comparing its harmonogram to other harmonograms of other sounds and may respond to a user's submission of the query sound by providing an identifier of the query sound to the user.

摘要翻译： 在识别实时音频的示例上下文中，音频处理器机器访问表示查询声音的音频数据，并从音频数据创建频谱图。 光谱图的每个片段表示查询声音中不同的时间片。 对于每个时间片，音频处理器机器确定一个或多个主要频率和表示该主频率的所有能量及其谐波的组合的总能量值。 机器通过在每个时间片中以这些主要频率表示这些总能量值来创建一个谐波图。 因此，谐波图可以表示查询声音中最强的谐波分量。 该机器可以通过将其谐波图与其他声音的其他谐波图进行比较来识别查询声音，并且可以通过向用户提供查询声音的标识符来响应用户的查询声音的提交。

公开(公告)号：US20170024468A1

公开(公告)日：2017-01-26

申请号：US15282691

申请日：2016-09-30

申请人： iHeartMedia Management Services, Inc.

发明人： Dyon Anniballi

IPC分类号： G06F17/30

CPC分类号： G06F17/30743 ,  G06F17/30769

摘要： A method includes determining, at a processor of a device, an unordered match between a set of consecutive portions of a first audio fingerprint and a set of non-consecutive portions of a second audio fingerprint. The method also includes, in response to determining that a length of the unordered match satisfies a length criterion, outputting an indicator that the first audio fingerprint matches the second audio fingerprint.

摘要翻译： 一种方法包括在设备的处理器处确定第一音频指纹的一组连续部分和第二音频指纹的非连续部分的一组之间的无序匹配。 该方法还包括响应于确定无序匹配的长度满足长度标准，输出第一音频指纹与第二音频指纹匹配的指示符。

公开(公告)号：US09548830B2

公开(公告)日：2017-01-17

申请号：US14512663

申请日：2014-10-13

申请人： The Nielsen Company (US), LLC

发明人： Manjunath Puttappa Kariyappa ,  Srinivasa Rao Edara ,  Suresh Kumar Kulathumkal Kalayil

IPC分类号： G06F17/00 ,  H04H60/58 ,  G06F3/16

CPC分类号： G06F17/30743 ,  G06F3/165 ,  G11B20/10527 ,  H04H60/37 ,  H04H60/58 ,  H04H2201/90

摘要： Methods and apparatus to generate signatures representative of media are disclosed. An example method includes transforming a block of samples from a time-domain representation to a frequency-domain representation comprising multiple frequency bands, determining a signature function by fitting a curve to at least a subset of the frequency bands, and calculating signature values for the block. Calculating the tuple includes calculating a first angle between a reference line and a first line that is tangent to the signature function at a first index, calculating a second angle between the reference line and a second line that is tangent to the signature function at a second index, calculating a third angle between the reference line and a third line that is tangent to the signature function at a third index, and creating the signature values based on the first angle, the second angle, and the third angle.

摘要翻译： 公开了生成代表媒体的签名的方法和装置。 示例性方法包括将来自时域表示的样本块变换为包括多个频带的频域表示，通过将曲线拟合到至少一个频带的子集来确定签名函数，以及计算签名值 块。 计算所述元组包括计算在第一索引处与所述签名函数相切的参考线与第一线之间的第一角度，计算所述参考线与第二线之间的第二角度，所述第二角度与所述签名功能的第二线成正切 索引，在第三索引处计算参考线和与签名函数相切的第三线之间的第三角度，以及基于第一角度，第二角度和第三角度创建签名值。

公开(公告)号：US09547715B2

公开(公告)日：2017-01-17

申请号：US13564302

申请日：2012-08-01

申请人： Lie Lu ,  Bin cheng

发明人： Lie Lu ,  Bin cheng

IPC分类号： G06F17/30 ,  G10L25/51 ,  G10L25/03 ,  G10L25/45

CPC分类号： G06F17/30743 ,  G10L25/03 ,  G10L25/45 ,  G10L25/51

摘要： Methods and apparatus for detecting a repetitive pattern in a sequence of audio frames are described. Similarity values of a first similarity matrix with first resolution for the sequence are calculated. An adaptive threshold is estimated from the similarity values for classifying the similarity values into repetition or non-repetition. For each of one or more offsets of a second similarity matrix with second resolution higher that the first resolution, similarity values of the second similarity matrix corresponding to the offset are calculated. Then the calculated similarity values are binarized with the adaptive threshold to obtain binarized data. Finally, the repetitive pattern is detected from the binarized data. The requirement on memory may be reduced because less data are stored in detecting the repetitive pattern.

摘要翻译： 描述了用于检测音频帧序列中的重复模式的方法和装置。 计算具有序列的第一分辨率的第一相似矩阵的相似度值。 从相似性值估计自适应阈值，用于将相似度值分类为重复或非重复。 对于具有第二分辨率高于第一分辨率的第二相似度矩阵的一个或多个偏移中的每一个，计算与偏移相对应的第二相似度矩阵的相似度值。 然后将所计算的相似度值用自适应阈值二值化，以获得二值化数据。 最后，从二值化数据中检测重复模式。 可以减少对存储器的要求，因为在检测重复模式时存储较少的数据。

公开(公告)号：US09537913B2

公开(公告)日：2017-01-03

申请号：US14147322

申请日：2014-01-03

申请人： Adam Elia Kidron

发明人： Adam Elia Kidron

IPC分类号： H04L29/06 ,  G06F17/30 ,  H04L29/08 ,  H04W4/18

CPC分类号： H04L65/4069 ,  G06F17/30743 ,  H04L65/4084 ,  H04L65/80 ,  H04L67/04 ,  H04L67/26 ,  H04W4/18

摘要： A music service application that can be run on a wireless mobile device enables audio data to be progressively downloaded from a remote server and also enables locally stored data to be played efficiently. Audio content that is relevant to a user is identified and downloaded to the user's mobile device, in some cases with minimal or no effort by the user. Continuous play features ensure that the user can experience an uninterrupted music experience, both in online and offline modes. Social features such as playlists and preferences of other users are leveraged, to provide users with popular music that is relevant to their interests.

摘要翻译： 可以在无线移动设备上运行的音乐服务应用使得能够从远程服务器逐渐下载音频数据，并且还使得能够有效地播放本地存储的数据。 与用户相关的音频内容被识别并下载到用户的移动设备，在某些情况下用户最少或不用努力。 连续播放功能可确保用户在线和离线模式下都能体验不间断的音乐体验。 利用其他用户的播放列表和偏好等社交功能，为用户提供与其兴趣相关的流行音乐。

公开(公告)号：US09535993B2

公开(公告)日：2017-01-03

申请号：US12482586

申请日：2009-06-11

申请人： James D. Bennett

发明人： James D. Bennett

IPC分类号： G06F17/30 ,  G06Q30/02

CPC分类号： G06Q20/1235 ,  G06F17/30017 ,  G06F17/30244 ,  G06F17/30569 ,  G06F17/3074 ,  G06F17/30743 ,  G06F17/30781 ,  G06F17/30858 ,  G06F17/30861 ,  G06F17/30864 ,  G06Q30/02 ,  G06Q30/0256 ,  G06Q30/0283 ,  G06Q30/04

摘要： A search engine server supports crawling of third party servers communicatively coupled to the search engine server to gather vectors to web content, wherein the search engine server delivers a report to registered creative work owners by identifying vectors to web content that contain similarities to their works and by providing protection to the copyrighted creative works. The search engine server has components that identify similarities to the works of the registered owners of the creative works and provide protection by reporting to the registered owners as well as host third party servers, in case of textual, image, audio and video creative works. This service is an added value based service of the search engine server to the registered owners of the creative works upon service charge basis. The search engine server also provides additional services that include reporting to the host third party servers that contain web content having similarities to that of creative works of registered owners and assisting the third party servers to delete the content upon consideration.

摘要翻译： 搜索引擎服务器支持爬行通信地耦合到搜索引擎服务器的第三方服务器以将向量收集到web内容，其中搜索引擎服务器通过向包含与其作品相似的web内容识别向量向向注册的创意作品所有者递送报告， 通过保护受版权保护的创作作品。 搜索引擎服务器具有与创意作品的注册所有者的作品相似的组件，并通过向注册的所有者以及主机第三方服务器报告，以便在文字，图像，音频和视频创意作品的情况下提供保护。 该服务是基于服务费用的创意作品的注册所有者的搜索引擎服务器的附加值服务。 搜索引擎服务器还提供附加服务，其中包括向主机第三方服务器报告包含与注册所有者的创意作品相似的网页内容，并协助第三方服务器在考虑时删除内容。

公开(公告)号：US20160350416A1

公开(公告)日：2016-12-01

申请号：US15114930

申请日：2015-02-09

申请人： NEC CORPORATION

发明人： Masato ISHII

IPC分类号： G06F17/30

CPC分类号： G06F17/30743 ,  G06F17/30247 ,  G06F17/30766 ,  G06K9/6223

摘要： Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

摘要翻译： 提供了一种搜索系统，其被配置为基于输入向量和注册向量之间的相似度来搜索与多个注册向量中的输入向量相似的注册向量。 搜索系统包括部分相似度计算单元，其计算作为与输入向量和登记向量的一个或多个维度中的一些相关的相似度的部分相似度的程度;限制计算单元，基于 计算部分相似度的程度，计算相似度时期望的相似程度的上限;以及拒绝判定单元，根据相似度的上限判定是否拒绝 来自搜索结果候选者的注册向量。

公开(公告)号：US20160350065A1

公开(公告)日：2016-12-01

申请号：US15232816

申请日：2016-08-10

申请人： Haim Nachum Markovitz ,  Alon Markovitz

发明人： Haim Nachum Markovitz ,  Alon Markovitz

IPC分类号： G06F3/16 ,  H04W64/00 ,  G10L17/22 ,  G06F17/30

CPC分类号： G06F3/162 ,  G06F3/165 ,  G06F17/30743 ,  G06F17/30749 ,  G06F17/30761 ,  G06F17/30769 ,  G06F17/30778 ,  G06F17/30864 ,  G10L13/00 ,  G10L17/22 ,  G10L25/48 ,  H04N21/25891 ,  H04N21/2668 ,  H04W64/006

摘要： A personalized car radio system comprising: a remote application server comprising: a collector, being a software that scans web sites continuously, for detecting content that corresponds to keywords expressing a driver's preferences; a client application, being a software that schedules displaying collected content in accordance with an alertness rank of the driver and a rhythm of the content; and a client device interacting with the application server by Unicast communication, the client device comprising: a safety module, being a software activated continuously or intermittently, for determining an alertness rank according to (a) metered movement of an organ of the driver, and (b) road condition; and a sounding device and a user interface thereof, for sounding the scheduled content; and a text-to-speech converter, being executed either on the server or the client device, for converting text files to audio files.

摘要翻译： 一种个性化的无线电系统，包括：远程应用服务器，包括：收集器，作为连续扫描网站的软件，用于检测对应于表示驾驶员偏好的关键字的内容; 客户端应用程序，是根据驾驶员的警觉等级和内容的节奏来安排显示收集的内容的软件; 以及客户端设备，通过单播通信与应用服务器交互，所述客户端设备包括：安全模块，其是被连续地或间歇地激活的软件，用于根据（a）驾驶员的器官的计量运动来确定警觉等级，以及 （二）道路状况; 以及用于对所调度的内容进行声音的探测设备及其用户界面; 以及在服务器或客户端设备上执行用于将文本文件转换成音频文件的文本到语音转换器。

公开(公告)号：US09507776B2

公开(公告)日：2016-11-29

申请号：US14163151

申请日：2014-01-24

申请人： Trio Systems LLC

发明人： Alan Bartholomew

IPC分类号： G06F17/30

CPC分类号： G06F17/30017 ,  G06F17/30321 ,  G06F17/30743 ,  G06F17/30749 ,  G06F17/30997

摘要： The invention described herein is generally directed to a method and apparatus for creating and retrieving audio data. In one implementation the invention comprises an annotation system configured to record, store, and retrieve media. The annotation system contains a set of client-processing devices configured to capture media for subsequent playback. Each client-processing device typically contains a record button to initiate the capture and is configured upon performing the capture operation to trigger an association of a unique ID with the media. The client-processing devices are further configured to upload the media and a unique ID to a server for purposes of storage. The server obtains the media and unique ID for subsequent retrieval and provides the media and the unique ID to at least one client-processing device from the set of client processing devices.

摘要翻译： 本文描述的发明一般涉及用于创建和检索音频数据的方法和装置。 在一个实现中，本发明包括被配置为记录，存储和检索介质的注释系统。 注释系统包含一组客户端处理设备，配置为捕获媒体以供后续播放。 每个客户处理设备通常包含用于发起捕获的记录按钮，并且在执行捕获操作以便触发唯一ID与媒体的关联时被配置。 客户处理设备还被配置为将媒体和唯一ID上传到服务器以存储目的。 服务器获得用于后续检索的媒体和唯一ID，并从该组客户端处理设备向至少一个客户端处理设备提供媒体和唯一ID。

公开(公告)号：US20160342594A1

公开(公告)日：2016-11-24

申请号：US14716334

申请日：2015-05-19

申请人： SPOTIFY AB

发明人： Tristan Jehan

IPC分类号： G06F17/30 ,  G06F7/36

CPC分类号： G06F17/30038 ,  G06F7/36 ,  G06F17/3002 ,  G06F17/30743 ,  G06F17/30787 ,  G06F17/30843

摘要： An excerpt of a media object is extracted by computing, for each bar of an N-bar loop, one or more perceptual quality vectors. For each of the one or more perceptual quality vectors within a search zone (S), one or more distances between bar i and bar i+N is computed and sorted to generate a sorted list of bars.

摘要翻译： 通过对于N条循环的每个条来计算一个或多个感知质量向量来提取媒体对象的摘录。 对于搜索区域（S）内的一个或多个感知质量向量中的每个，计算条i和条i + N之间的一个或多个距离并对其进行排序以生成排序的条列表。