Media browser using multimodal analysis

Abstract

A media browser, graphical user interface and method for browsing a media file wherein a user selects at least one feature in a media file and is provided with information regarding the existence of the selected feature in the media file. Based on the information, the user can identify and playback portions of interest in a media file. Features in a media file, such as a speaker's identity, applause, silence, motion, or video cuts, are preferably automatically time-wise evaluated in the media file using known methods. Metadata generated based on the time-wise feature evaluation are preferably mapped to confidence score values that represent a probability of a corresponding feature's existence in the media file. Confidence score information is preferably presented graphically to a user as part of a graphical user interface, and is used to interactively browse the media file.

What is claimed is:  
     
         1 . A media browser comprising: 
 a feature selection module that inputs at least one media feature selected by a user;    a media presentation device that provides an aural and/or visual representation of a media file being browsed; and    a feature indicator that provides information related to a confidence score for at least one selected media feature, the confidence score indicating a probability of existence of a corresponding selected media feature in the media file;    wherein the selected media feature is not used to perform, and is not related to, a text search of the media file.    
     
     
         2 . A method of browsing a media file, comprising: 
 selecting a feature of a media file being browsed, the feature not being used to perform and not related to a text search of the media file;    providing information related to a confidence score for at least one selected feature relative to a segment of the media file, the confidence score indicating a probability of existence of a corresponding selected feature in the media file; and    selecting a portion of the media file based on the information related to a confidence score for at least one selected feature.    
     
     
         3 . A graphical user interface for reviewing a portion of a stored data set, the stored data set including at least one of audio data and video data, the graphical user interface comprising: 
 a feature selection portion through which a user can select at least one data feature of the data set, the selected feature not related to, and not used to perform, a text search of the data set;    at least one data representation portion, each data representation portion representing the stored data set relative to one selected feature and containing at least one selectable feature indicator, each selectable feature indicator corresponding to a portion of the stored data set and providing information to the user related to a confidence score that indicates a probability of existence that the corresponding portion of the stored data set contains the corresponding selected feature.