公开(公告)号：US20140019390A1

公开(公告)日：2014-01-16

申请号：US13941727

申请日：2013-07-15

Applicant: UMAMI, CO.

Inventor： Aron Glennon ,  Eric Humphrey ,  Bryan Slavin ,  Scott Rosenberg

IPC: G06N5/02 ,  G06N99/00

CPC classification number: G06N5/02 ,  G06F16/683 ,  G06N3/0454 ,  G06N3/084 ,  G06N20/00 ,  G10L25/30 ,  G10L25/54

Abstract: Apparatus and method for fingerprinting an audio signal utilizes programmed machine to identify overlapping windows in a time domain representation of the audio signal, establish a frequency domain representation of the overlapping windows, convolve a set of two-dimensional kernels with the frequency domain representation to thereby provide a convolutional layer as an output stage, reduce dimensionality of the convolution layer to provide one or more further output stages, and perform further processing so as to output a decision in regard to a plurality of the overlapping windows comprising either a specific content id that matches to the audio signal or a failure-to-match indication.

Abstract translation: 用于指纹音频信号的装置和方法利用编程机来识别音频信号的时域表示中的重叠窗口，建立重叠窗口的频域表示，从而将一组二维内核与频域表示进行卷积，由此 提供卷积层作为输出级，降低卷积层的维度以提供一个或多个另外的输出级，并且执行进一步的处理，以便输出关于多个重叠窗口的决定，所述多个重叠窗口包括特定内容id 与音频信号匹配或失败匹配指示。

公开(公告)号：US20130111514A1

公开(公告)日：2013-05-02

申请号：US13621277

申请日：2012-09-16

Applicant: Umami Co.

Inventor： Bryan SLAVIN ,  Scott Rosenberg ,  Aron Glennon

IPC: H04N21/442

CPC classification number: H04N21/442 ,  G06F16/433 ,  G06F16/60 ,  H04H60/58 ,  H04H60/64 ,  H04H2201/40 ,  H04N21/4126 ,  H04N21/42203 ,  H04N21/4307 ,  H04N21/4394 ,  H04N21/4722 ,  H04N21/8126

Abstract: Interactive digital media platform, methods and apparatus for detecting and dynamically synchronizing to media content (e.g., television (TV) programs or movies) that a viewer is watching while providing related content on a second screen for enhancing the viewer experience. In one embodiment, the primary content is determined by detecting an audio signal of the primary content via the second screen device; the audio signal may then be processed to generate a fingerprint for comparison with a data store of primary content. The primary content can be classified by various categories (e.g., unique program, advertising, repeat airing, theme song . . . ) and the classification used to aid in the identification and/or in selection of the content to be presented on the interactive second screen device. The system allows a substantially real time comparison and recognition of what primary content a viewer is watching on a first screen device and presentation to the user of content that is substantially synchronous to the viewer's location in the primary content. The viewer can actively engaged with the content presented and can share the content with others via social networking and the like.

Abstract translation: 交互式数字媒体平台，用于检测和动态地同步于观众正在观看的媒体内容（例如电视（TV）节目或电影）的方法和装置，同时在第二屏幕上提供相关内容以增强观众体验。 在一个实施例中，通过经由第二屏幕设备检测主要内容的音频信号来确定主要内容; 然后可以处理音频信号以产生用于与主要内容的数据存储进行比较的指纹。 主要内容可以按各种类别（例如，独特的节目，广告，重复播放，主题曲等）分类，以及用于帮助识别和/或选择要在互动式第二个上呈现的内容的分类 屏幕设备。 该系统允许基本上实时地比较和识别观看者在第一屏幕设备上观看的主要内容以及向用户呈现与观看者在主要内容中的位置基本同步的内容的内容。 观众可以积极地参与呈现的内容，并且可以通过社交网络等与他人分享内容。