公开(公告)号：US20070041667A1

公开(公告)日：2007-02-22

申请号：US11445928

申请日：2006-06-02

Applicant: Ingemar Cox

Inventor： Ingemar Cox

IPC: G06K9/54 ,  G06K9/46

CPC classification number: H04H60/37 ,  G06F17/30017 ,  G06F17/30026 ,  G06F17/30047 ,  G06Q30/02 ,  H04H60/58 ,  H04H2201/90 ,  H04N21/2407 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/812

Abstract: Information about an audio or video file played on a device is provided by (a) extracting features from the audio or video file, (b) communicating the features to a database, and (c) receiving the information about the audio or video file from the database. The information might include a song title, an album title, and/or a performer name. The information might include a title of a video work, a director of the video work, and/or names of performers in the video work. The information might be rendered on an output of the device. The information might be stored (e.g., persistently) locally on the device.

Abstract translation: 通过以下方式提供关于在设备上播放的音频或视频文件的信息：（a）从音频或视频文件中提取特征，（b）将功能传达到数据库，以及（c）从音频或视频文件 数据库。 该信息可以包括歌曲标题，专辑标题和/或表演者名称。 信息可能包括视频作品的标题，视频作品的导演和/或视频作品中表演者的姓名。 信息可能会在设备的输出上呈现。 该信息可能本地存储在设备上（例如，永久存储）。

公开(公告)号：US20050086682A1

公开(公告)日：2005-04-21

申请号：US10686240

申请日：2003-10-15

Applicant: Christopher Burges ,  Cormac Herley

Inventor： Christopher Burges ,  Cormac Herley

IPC: G06F17/30 ,  G06F17/00 ,  G06K9/00 ,  H04H1/00 ,  H04H20/38 ,  H04H20/82 ,  H04H60/44 ,  H04H60/73 ,  H04N5/76 ,  H04N7/08 ,  H04N7/173 ,  H04N21/232 ,  H04N21/845 ,  H04N7/16 ,  H04H9/00

CPC classification number: H04H20/16 ,  H04H20/14 ,  H04H20/38 ,  H04H20/82 ,  H04H60/44 ,  H04H60/73 ,  H04H2201/90 ,  H04N7/17318 ,  H04N21/25891 ,  H04N21/26603 ,  H04N21/278 ,  H04N21/47202 ,  H04N21/4828 ,  H04N21/8456

Abstract: Information about media objects within media streams is inferred based on repeat instances of the media objects within the media streams. A system and methods enable the monitoring of one or more media streams and the identification of repeat instances of media objects (e.g., audio and/or video objects) within the media streams. The monitoring and object repeat identification is performed by one or more server computers on a network. Information about a media object can be inferred based on repeat instances of the media object and based on repeat instances of related media objects. The information is transferred from a server to a client in response to a user query entered at the client through an interactive user interface.

Abstract translation: 基于媒体流内的媒体对象的重复实例来推断关于媒体流内的媒体对象的信息。 系统和方法使得能够监视一个或多个媒体流以及媒体流中媒体对象（例如，音频和/或视频对象）的重复实例的识别。 监视和对象重复标识由网络上的一台或多台服务器计算机执行。 可以基于媒体对象的重复实例并基于相关媒体对象的重复实例来推断关于媒体对象的信息。 响应于通过交互式用户界面在客户端输入的用户查询，将信息从服务器传送到客户端。

公开(公告)号：US20040226035A1

公开(公告)日：2004-11-11

申请号：US10839108

申请日：2004-05-05

Inventor： David L. Hauser JR.

IPC: H04N007/16 ,  H04H009/00 ,  H04N007/00 ,  H04N005/91

CPC classification number: G11B27/11 ,  G11B27/034 ,  G11B2220/20 ,  H04H60/16 ,  H04H60/17 ,  H04H60/20 ,  H04H60/27 ,  H04H60/375 ,  H04H60/56 ,  H04H60/59 ,  H04H2201/90 ,  H04N5/76 ,  H04N5/782 ,  H04N5/9201 ,  H04N21/4334 ,  H04N21/4396 ,  H04N21/44008 ,  H04N21/440281 ,  H04N21/4508 ,  H04N21/4542 ,  H04N21/812

Abstract: A central database provides a location for creating and storing samples of known television commercials. The database of commercial samples is downloaded to a set-top box via a communicate link. The set-top box incorporates a processor for comparing a television signal with the database of known commercial messages to detect the presence of commercial messages. The set-top box may be used to control a recording unit to stop recording for the duration of the commercial message or flag the commercial message for muting or manual skipping during playback. Using this system, the user has the ability to positively detect commercial messages and eliminate the commercials from viewing if desired.

Abstract translation: 中央数据库提供用于创建和存储已知电视广告的样本的位置。 商业样本的数据库通过通信链路下载到机顶盒。 机顶盒包括一个处理器，用于将电视信号与已知商业消息的数据库进行比较，以检测商业消息的存在。 机顶盒可以用于控制记录单元在商业消息的持续时间内停止记录，或者标记用于在播放期间静音或手动跳过的商业消息。 使用该系统，用户能够积极地检测商业消息，并且如果需要，消除广告的观看。

公开(公告)号：US20030131350A1

公开(公告)日：2003-07-10

申请号：US09973893

申请日：2002-01-08

Inventor： John C. Peiffer ,  Michael A. Hicks ,  David Howell Wright ,  Paul Mark Mears ,  Venugopal Srinivasan ,  Daozheng Lu ,  Paul C. Kempter

IPC: H04N007/16 ,  H04H009/00 ,  H04B003/00

CPC classification number: H04H60/59 ,  H04H60/37 ,  H04H60/58 ,  H04H2201/90 ,  H04N7/17318 ,  H04N21/235 ,  H04N21/4331 ,  H04N21/4394 ,  H04N21/44213 ,  H04N21/812 ,  H04N21/8352

Abstract: Method and apparatus for identifying broadcast digital audio signals include structure and/or function whereby the digital audio signal is provided to processing structure which is configured to (i) identify a program-identifying code in the received digital audio signal, (ii) identify a program-identifying code in a decompressed received digital audio signal, (iii) identify a feature signature in the received digital audio signal, and (iv) identify a feature signature in the decompressed received digital audio signal. Preferably, such processing structure is disposed in a dwelling or a monitoring site in an audience measurement system, such as the Nielsen TV ratings system.

Abstract translation: 用于识别广播数字音频信号的方法和装置包括其中数字音频信号被提供给处理结构的结构和/或功能，处理结构被配置为（i）识别所接收的数字音频信号中的节目识别码，（ii） 解码接收的数字音频信号中的节目识别码，（iii）识别所接收的数字音频信号中的特征签名，以及（iv）识别解压缩的接收的数字音频信号中的特征签名。 优选地，这种处理结构被布置在诸如尼尔森电视评级系统的观众测量系统中的住宅或监视站点中。

公开(公告)号：US20030014755A1

公开(公告)日：2003-01-16

申请号：US09905124

申请日：2001-07-13

Inventor： Marvin Lynn Williams

IPC: H04N007/025 ,  H04N007/10 ,  H04N007/16 ,  H04N007/20 ,  H04N007/173 ,  H04Q007/20

CPC classification number: H04H20/106 ,  H04H20/30 ,  H04H20/93 ,  H04H2201/90 ,  H04N7/08 ,  H04N21/25891 ,  H04N21/41407 ,  H04N21/418 ,  H04N21/4524 ,  H04N21/458 ,  H04N21/835 ,  H04N21/8543 ,  H04N21/8547

Abstract: A method and apparatus for correlating the transmission of audio-video segments to digital signatures over a wireless or non-wireless medium to allow for real-time substitution and processing of audio and video programs. In one embodiment at least one digital signature having a correlated audio-video segment is transmitted as a digital waveform within an analog modulated signal representing the audio-video segment. The analog modulated signal is transmitted to a wireless receiver. The wireless receiver demodulates the digital waveforms while concurrently playing the correlated audio-video segment. An electronic user interface enables the wireless receiver to define conditional preferences to actively scan a plurality of channels and Internet addresses to substitute a currently playing audio-video segment with a preferred audio-video segment. In an alternative embodiment, a distributed computer network is the broadcast system transmitting digital signatures to either a wireless or non-wireless computer.

Abstract translation: 一种用于通过无线或非无线介质将音频 - 视频段与数字签名的传输相关联以允许音频和视频节目的实时替换和处理的方法和装置。 在一个实施例中，具有相关音频 - 视频段的至少一个数字签名作为表示音频 - 视频段的模拟调制信号中的数字波形发送。 模拟调制信号被发送到无线接收机。 无线接收机在同时播放相关音频 - 视频片段的同时解调数字波形。 电子用户界面使得无线接收机能够定义条件偏好以主动扫描多个频道和因特网地址以用当前播放的音频 - 视频段替换优选的音频 - 视频段。 在替代实施例中，分布式计算机网络是向无线或非无线计算机传送数字签名的广播系统。

公开(公告)号：US20020178410A1

公开(公告)日：2002-11-28

申请号：US10073772

申请日：2002-02-11

Inventor： Jaap Andre Haitsma ,  Antonius Adrianus Cornelis Maria Kalker ,  Constant Paul Marie Jozef Baggen ,  Job Cornelis Oostveen

IPC: H03M013/00

CPC classification number: H04H60/37 ,  G06F17/30743 ,  G06F17/30787 ,  G06F17/30802 ,  G06K9/00744 ,  G06T1/0028 ,  G06T1/005 ,  G06T2201/0051 ,  G06T2201/0061 ,  G06T2201/0065 ,  G10H1/0058 ,  G10H2210/295 ,  G10H2240/061 ,  H03M7/30 ,  H04H60/56 ,  H04H2201/90 ,  H04N19/467

Abstract: Hashes are short summaries or signatures of data files which can be used to identify the file. Hashing multimedia content (audio, video, images) is difficult because the hash of original content and processed (e.g. compressed) content may differ significantly. The disclosed method generates robust hashes for multimedia content, for example, audio clips. The audio clip is divided (12) into successive (preferably overlapping) frames. For each frame, the frequency spectrum is divided (15) into bands. A robust property of each band (e.g. energy) is computed (16) and represented (17) by a respective hash bit. An audio clip is thus represented by a concatenation of binary hash words, one for each frame. To identify a possibly compressed audio signal, a block of hash words derived therefrom is matched by a computer (20) with a large database (21). Such matching strategies are also disclosed. In an advantageous embodiment, the extraction process also provides information (19) as to which of the hash bits are the least reliable. Flipping these bits considerably improves the speed and performance of the matching process.

Abstract translation: 哈希是数据文件的简短摘要或签名，可用于标识文件。 哈希多媒体内容（音频，视频，图像）是困难的，因为原始内容的哈希和处理（例如压缩的）内容可能会显着不同。 所公开的方法为多媒体内容（例如，音频剪辑）生成鲁棒散列。 音频剪辑被分割成连续的（优选重叠的）帧。 对于每个帧，频谱被分成（15）到频带。 计算每个频带（例如能量）的鲁棒性质（16）并通过相应的散列比特（17）表示。 因此，音频剪辑由二进制散列字的连接表示，每个帧一个。 为了识别可能压缩的音频信号，由计算机（20）与大数据库（21）匹配从其导出的散列字块。 还披露了这种匹配策略。 在有利的实施例中，提取过程还提供关于哪个散列位是最不可靠的信息（19）。 翻转这些位可显着提高匹配过程的速度和性能。

公开(公告)号：US20020059633A1

公开(公告)日：2002-05-16

申请号：US09955691

申请日：2001-09-19

Inventor： David H. Harkness ,  Daozheng Lu ,  William A. Feininger ,  Craig M. Smithpeters

IPC: H04N007/173

CPC classification number: H04H20/28 ,  H04H20/14 ,  H04H20/93 ,  H04H60/37 ,  H04H60/40 ,  H04H60/43 ,  H04H60/56 ,  H04H2201/90 ,  H04N21/44204 ,  H04N21/6582 ,  H04N21/8352

Abstract: A detection apparatus includes a tuner tuned to the program and a meter coupled to the tuner and arranged to detect content ancillary information from the program tuned by the tuner. The content ancillary information may be a media link, closed captioning information, or the like. The meter may also be arranged to extract a broadcast signature from the program. A comparator compares the broadcast signature to a reference signature selected from a library of reference signatures based upon the content ancillary information. Broadcast signatures from unknown programs may be clustered at least partially on the basis of the content ancillary information.

Abstract translation: 检测装置包括调谐到程序的调谐器和耦合到调谐器的仪表，并被布置成从由调谐器调谐的程序中检测内容辅助信息。 内容辅助信息可以是媒体链接，隐藏字幕信息等。 仪表还可以被布置成从程序中提取广播签名。 比较器基于内容辅助信息将广播签名与从参考签名库中选择的参考签名进行比较。 来自未知程序的广播签名可以至少部分地基于内容辅助信息进行聚类。

公开(公告)号：US20020059577A1

公开(公告)日：2002-05-16

申请号：US09909224

申请日：2001-07-19

Applicant: Nielsen Media Research, Inc.

Inventor： Daozheng Lu ,  Paul C. Kempter ,  William A. Feininger

IPC: H04N007/16

CPC classification number: H04N7/165 ,  H04H60/37 ,  H04H60/39 ,  H04H60/45 ,  H04H60/58 ,  H04H60/82 ,  H04H2201/90 ,  H04N21/4392 ,  H04N21/44222 ,  H04N21/658 ,  H04N21/812

Abstract: A television audience measurement system measures viewing of a television program viewed on digital television located in a statistically selected site by (i) retrieving an audience measurement data packet from a television set in order to identify the television program, (ii) detecting an audio code embedded in the television program in order to identify the television program, (iii) extracting an audio signature from the television program in order to identify the television program, (iv) identifying the television program through use of a software agent, and (v) selecting at least one of the retrieving means, the detecting means, the extracting means, and the software agent in order to identify the television program.

Abstract translation: 电视观众测量系统通过（i）从电视机中检索观众测量数据分组以便识别电视节目，（ii）检测音频代码，测量在位于统计选择的站点中的数字电视上观看的电视节目的观看次数 嵌入在电视节目中以识别电视节目，（iii）从电视节目中提取音频签名以识别电视节目，（iv）通过使用软件代理识别电视节目，以及（v） 选择检索装置，检测装置，提取装置和软件代理中的至少一个，以识别电视节目。

公开(公告)号：US20020026635A1

公开(公告)日：2002-02-28

申请号：US09859764

申请日：2001-05-17

Applicant: Nielsen Media Research, Inc.

Inventor： Henry B. Wheeler ,  Daozheng Lu

IPC: H04N007/16 ,  H04H009/00

CPC classification number: H04H60/39 ,  H04H60/41 ,  H04H60/56 ,  H04H2201/90 ,  H04N7/173 ,  H04N21/235 ,  H04N21/435 ,  H04N21/44222 ,  H04N21/6582 ,  H04N21/8352

Abstract: A system identifies which of first and second signal sources is supplying a program signal to a monitored receiver. The first and second signal sources and the monitored receiver are located in a household. The system extracts a reference program signature representative of an output of the monitored receiver and first and second source program signatures representative of an output of the first and second signal sources. The system identifies-which of the first and second signal sources is a source of the program signal in response to the reference program signature and the first and second source program signatures.

Abstract translation: 系统识别第一和第二信号源中的哪一个正向受监视的接收机提供节目信号。 第一和第二信号源和受监控的接收器位于家庭中。 系统提取表示监视的接收机的输出的参考程序签名，以及表示第一和第二信号源的输出的第一和第二源程序签名。 系统识别 - 响应于参考程序签名和第一和第二源程序签名，第一和第二信号源中的哪一个是程序信号的源。

公开(公告)号：US5572246A

公开(公告)日：1996-11-05

申请号：US486511

申请日：1995-06-07

Applicant: Michael D. Ellis ,  Stephen M. Dunn ,  Michael W. Fellinger ,  Fancy B. Younglove ,  David M. James ,  David L. Clifton ,  Richard S. Land

Inventor： Michael D. Ellis ,  Stephen M. Dunn ,  Michael W. Fellinger ,  Fancy B. Younglove ,  David M. James ,  David L. Clifton ,  Richard S. Land

IPC: H04N17/00 ,  G06K9/00 ,  G06K9/62 ,  G06K9/70 ,  G06K9/78 ,  G06T7/00 ,  H04H1/00 ,  H04H60/37 ,  H04H60/58 ,  H04H60/59 ,  H04N7/10 ,  H04N9/00 ,  H04N17/04

CPC classification number: G06K9/00711 ,  G06F17/30802 ,  H04H60/372 ,  H04H60/58 ,  H04H60/59 ,  H04H2201/90

Abstract: Signatures are produced for characterizing an interval of a video signal representing a picture for use in broadcast segment recognition. The signature is produced based on portions of the video signal representing corresponding regions of the picture each spaced by a certain amount from a nominal edge of the picture. A shift in the video signal corresponding with a shift in the edge of the picture from a nominal edge of the picture is detected. The portions of the video signal are adjusted to compensate for the shift in the edge of the picture and a signature is produced based on the adjusted portions of the video signal.

Abstract translation: 产生用于表征表示用于广播段识别的图像的视频信号的间隔的签名。 签名是基于表示图像的相应区域的视频信号的部分产生的，每个区域与图像的标称边缘间隔一定量。 检测与图像的边缘的偏移相对应的视频信号从图像的标称边缘的偏移。 调整视频信号的部分以补偿图像边缘的偏移，并且基于视频信号的调整部分产生签名。