System and method for identifying and segmenting repeating media objects embedded in a stream

Abstract

An “object extractor” automatically identifies and segments repeating media objects in a media stream. “Objects” are any section of non-negligible duration, i.e., a song, video, advertisement, jingle, etc., which would be considered to be a logical unit by a human listener or viewer. Identification and segmentation of repeating objects is achieved by directly comparing sections of the media stream to identify matching portions of the stream, then aligning the matching portions to identify object endpoints. Alternately, a suite of object dependent algorithms is employed to target particular aspects of the stream for identifying possible objects within the stream. Confirmation of possible objects as repeating objects is achieved by automatically searching for potentially matching objects in a dynamic object database, followed by a detailed comparison to one or more of the potentially matching objects. Object endpoints are then determined by automatic alignment and comparison to other copies of that object.

Description

CROSS REFERENCE TO RELATED APPLICATIONS [0001] This application is a Divisional Application of U.S. patent application Ser. No. 10 / 187,774, filed on July 1st, 2002, by Cormac Herley and entitled “A SYSTEM AND METHOD FOR IDENTIFYING AND SEGMENTING REPEATING MEDIA OBJECTS EMBEDDED IN A STREAM”.BACKGROUND [0002] 1. Technical Field [0003] The invention is related to media stream identification and segmentation, and in particular, to a system and method for identifying and extracting repeating audio and / or video objects from one or more streams of media such as, for example, a media stream broadcast by a radio or television station. [0004] 2. Related Art [0005] There are many existing schemes for identifying audio and / or video objects such as particular advertisements, station jingles, or songs embedded in an audio stream, or advertisements or other videos embedded in a video stream. For example, with respect to audio identification, many such schemes are referred to as “audio fingerprin...

AI Technical Summary

Benefits of technology

The patent describes a system and method for automatically identifying and segmenting repeating objects in a media stream, such as songs, jingles, and advertisements. This is a challenging problem because the objects are often corrupted by noise and distortion, and there is no reliable way to distinguish them from non-repeating objects. The system uses a combination of techniques to extract and segment these repeating objects, including pattern recognition, voice-overs, and time-frequency analysis. The system can identify and store only desirable content from the media stream, and can also de-noise and clear up objects that are repeated throughout the stream. The system can be used in a variety of applications, such as identifying and accessing desired content or automatically filtering out unwanted content.

Problems solved by technology

Without such a preexisting database, identification, and / or segmentation of the media stream are not possible when using the aforementioned conventional schemes.

However, automatically distinguishing the same, e.g., repeating, content automatically in a media stream is generally a difficult problem.

However, these objects will typically occur at unpredictable times within the media stream, and are frequently corrupted by noise caused by any acquisition process used to capture or record the media stream.

Further, objects in a typical media stream, such as a radio broadcast, are often corrupted by voice-overs at the beginning and / or end point of each object.

Additionally, such objects are often intentionally distorted.

Further, audio objects, such as music or a song, broadcast on a typical radio station are often cross-faded with the preceding and following music or songs, thereby obscuring the audio object start and end points, and adding distortion or noise to the object.

Consequently, identification of such objects and locating the endpoints for such objects in such a noisy environment is a challenging problem.

However, even in such a noisy environment, approximate endpoints are located by aligning the matching portions using any of a number of conventional techniques, such as simple pattern matching, aligning cross-correlation peaks between the matching portions, or any other conventional technique for aligning matching signals.

Further, because the database is initially empty, the likelihood of identifying potential matches naturally increases over time as more potential objects are identified and added to the database.

Images