Abstract: A method of generating an audio content index for use by a search engine includes determining a phoneme sequence based on recognized speech from an audio content time segment. The method also includes identifying k-phonemes which occur within the phoneme sequence. The identified k-phonemes are stored within a data structure such that the identified k-phonemes are capable of being compared with k-phonemes from a search query.
Type:
Grant
Filed:
April 30, 2007
Date of Patent:
July 19, 2011
Assignee:
Sonic Foundry, Inc.
Inventors:
Michael J. Knight, Jonathan Scott, Steven J. Yurick, John Hancock
Abstract: A rich media event production method and system including the capturing, indexing, and synchronizing of RGB-based graphic content. The method includes capturing audio and video during an event production; capturing graphical content during the event production from an RGB source device; indexing and synchronizing the captured audio, video, and graphical content during the event production; and communicating the audio, video, and graphical content over a network for presentation at a computer coupled to the network during or after the event production as selected by a user of the computer.
Abstract: A rich media event production method and system including the capturing, indexing, and synchronizing of RGB-based graphic content. The method includes capturing audio and video during an event production; capturing graphical content during the event production from an RGB source device; indexing and synchronizing the captured audio, video, and graphical content during the event production; and communicating the audio, video, and graphical content over a network for presentation at a computer coupled to the network during or after the event production as selected by a user of the computer.
Abstract: A system and method for detecting features in video from business meetings and video teleconferencing systems can use color, motion, morphological (shape) filtering and a set of heuristic rules to determine possible features in the scene. One embodiment includes obtaining a first video frame of images and a second video frame of images, performing a luminance conversion on the first video frame of images and the second video frame of images, performing a motion filter operation on the converted first and second frames of images, performing a chrominance normalization on the second video frame of images, performing a color filter operation on the normalized second video frame of images, and processing the first and second frames of video images after the motion filter and color filter operations.
Abstract: A rich media event production method and system including the capturing, indexing, and synchronizing of RGB-based graphic content. The method includes capturing audio and video during an event production; capturing graphical content during the event production from an RGB source device; indexing and synchronizing the captured audio, video, and graphical content during the event production; and communicating the audio, video, and graphical content over a network for presentation at a computer coupled to the network during or after the event production as selected by a user of the computer.
Abstract: The system and method herein capture, analyze, manage, and access disparate types and sources of media, biometric, and database information. The system and method build a unified and intelligent time-based view of individuals, regardless of data source or type. This view is possible by capturing media, biometric, and database information; processing that multi-modal information to extract, analyze and quickly sort through large volumes of digital information; and providing a user interface that can be configured to retrieve, view, manage, compare, and annotate captured information and analysis.
Abstract: The disclosure relates to a method of determining one or more periods of recurring events within a recorded signal, such as, music. This method can include establishing one or more anchor points in the recorded signal where an anchor point is indicative of a beginning point for a period of recurring events in the recorded signal, determining a length for the period of recurring events in the recorded signal where the length starts from the established anchor point and defines a first loop, and refining the length for the period of recurring events by comparing the first loop with subsequent loops. The subsequent loops have the length of the first loop.