Transcript Alignment

Abstract

An approach to alignment of transcripts with recorded audio is tolerant of moderate transcript inaccuracies, untranscribed speech, and significant non-speech noise. In one aspect, a number of search terms are formed from the transcript such that each search term is associated with a location within the transcript. Possible locations of the search terms are then determined in the audio recording. The audio recording and the transcript are then aligned using the possible locations of the search terms. In another aspect a search expression is accepted, and then a search is performed for spoken occurrences of the search expression in an audio recording. This search includes searching for text occurrences of the search expression in a text transcript of the audio recording, and searching for spoken occurrences of the search expression in the audio recording.

1 . One or more processor readable storage devices having code embodied on said storage devices, said code for programming one or more processors to perform a method comprising:
 accepting a transcript of a multimedia recording;   partially aligning a time interval of the multimedia recording with the transcript, including one of (i) omitting portions of the transcript from a result of the partial alignment, and (ii) aligning an incomplete transcript of the multimedia recording;   displaying in a user interface a textual representation of at least a portion of the transcript;   receiving input from a user selecting a segment of the textual representation;   using the result of the partial alignment of the transcript of the multimedia recording with the multimedia recording to select a portion of the multimedia recording that is associated with the selected segment of the textual representation; and   enabling further processing of the selected portion of the multimedia recording.   
     
     
         2 . The storage devices of  claim 1 , wherein the transcript of the multimedia recording comprises a script that is produced from the multimedia recording. 
     
     
         3 . The storage devices of  claim 1  having code embodied thereon for programming the one or more processors to perform the method of enabling further processing of the selected portion of the multimedia recording comprising:
 enabling the user to access the selected portion of the multimedia recording through the user interface.   
     
     
         4 . The storage devices of  claim 1 , wherein the selected portion of the multimedia recording contains the portion of the multimedia recording that corresponds with the selected segment of the textual representation. 
     
     
         5 . The storage devices of  claim 1 , wherein the portion of the multimedia recording that corresponds with the selected segment of the textual representation contains the selected portion of the multimedia recording.