Back to results
US 8,572,488 B2Granted
Spot dialog editor
AssigneeAvid Technology, Inc.
InventorsMichael E. Phillips, Glenn Lea
Life of this patent
Estimating the term…
Abstract
Automated methods are used to augment an original script of a time-based media program that contains speech with timing metadata and an indication of a confidence level with which script portions are matched with the speech in the program audio track. An editor uses a spot dialog editor tool to produce a word-accurate spot dialog master by reviewing and editing script portions displayed next to the corresponding portions of the time-based media. The spot dialog editor tool selects for review and editing the parts of the script having a low confidence match with the speech in the program.
Claims17
In a computer-based system, a method of conforming a script or transcript comprising words and phrases corresponding to a time-based media program that includes recorded speech, the method comprising:
- receiving the script or transcript;
- receiving timing information comprising, for each of a plurality of words or phrases within the script or transcript, a temporal location within the time-based media program where that word or phrase has been matched with a corresponding spoken word or phrase recognized in the recorded speech, and a confidence level for a match of the word or phrase from the selected portion of the script or transcript to the word or phrase recognized in the recorded speech;
- displaying a selected portion of the script or transcript;
- using the timing information, displaying, along with the word or phrases of the displayed selected portion of the script or transcript to which the confidence level corresponds, a graphical representation of the confidence levels for the matches of the words or phrases from the displayed selected portion of the script or transcript to the corresponding words or phrases recognized in the recorded speech from the temporal location within the time-based media program according to the received timing information, wherein at least one of the words or phrases within the selected portion has a confidence level equal to or lower than a predetermined threshold confidence level indicating that said at least one of the words or phrases in the selected portion do not match the words or phrases recognized in the recorded speech;
- retrieving a portion of the time-based media program corresponding to the temporal location associated with the selected portion of the script or transcript;
- playing back the retrieved portion of the time-based media program, while the selected portion of the script or transcript and graphical representation of the corresponding confidence levels are displayed, to enable a user to compare the retrieved portion of the time-based media program and the selected portion of the script or transcript;
- and
- in response to input received from the user, making corrections as indicated by the user to the text of the selected portion of the script or transcript so as to have the corrected text match the words or phrases in the recorded speech, such corrections being made while text from the selected portion of the script or transcript and corresponding graphical representations of the confidence levels are displayed and the corresponding portion of the time-based media is played back.
5 more elements
In a computer-based system, a method of conforming a transcript comprising words and phrases of dialog to a dialog audio track of a time-based media program, the method comprising:
- receiving an augmented version of the transcript and, for each word or phrase of a plurality of the words and phrases within the transcript, timing information comprising a temporal location within the time-based media program where the word or phrase is spoken in the dialog audio track, and a confidence level indicating a quality of a match between each of the words or phrases from the transcript and words or phrases recognized in their corresponding identified temporal location within the time-based media;
- receiving the time-based media program;
- and
- providing an interactive graphical interface for a user, the graphical interface including a transcript display portion for displaying text from a portion of the transcript and a media display portion, simultaneously displayed with the transcript display portion, for displaying a portion of the time-based media program spanning the identified temporal location corresponding to the displayed text from the portion of the transcript according to the timing information;
- displaying text from the portion of the transcript in the transcript display portion, wherein the text from the transcript is displayed with a visual attribute corresponding to the confidence levels for matches of the text from the portion of the transcript according to the timing information;
- in response to a request from the user, playing the portion of the time-based media in the media display portion while the corresponding text and visual attribute corresponding to the confidence levels are displayed in the transcript display portion;
- and
- enabling the user to make corrections to the displayed text from the transcript in the transcript display portion so as to have the text match the words or phrases spoken in the dialog audio track while the text from the portion of the transcript and the corresponding visual attribute corresponding to the corresponding confidence level are displayed and the corresponding portion of the time-based media is played.
5 more elements
A computer program product, comprising:
- a computer-readable medium;
- and
- computer program instructions encoded on the computer-readable medium, wherein the computer program instructions, when processed by a computer, instruct the computer to perform a method for editing time-based media that includes recorded speech, the method comprising:
- receiving the script or transcript;
- receiving timing information comprising, for each of a plurality of words or phrases within the script or transcript, a temporal location within the time-based media program where that word or phrase has been matched with a corresponding spoken word or phrase recognized in the recorded speech, and a confidence level for a match of the word or phrase from the selected portion of the transcript to the spoken word or phrase recognized in the recorded speech from the associated temporal location within the time-based media program;
- displaying a selected portion of the script or transcript;
- using the timing information, displaying, along with the word or phrases of the displayed selected portion of the script or transcript to which the confidence level corresponds, a graphical representation of the confidence levels for the matches of the words or phrases from the displayed selected portion of the script or transcript to the corresponding words or phrases recognized in the recorded speech from the temporal location within the time-based media program according to the received timing information, wherein at least one of the words or phrases within the selected portion has a confidence level equal to or lower than a predetermined threshold confidence level, indicating that said at least one of the words or phrases in the selected portion do not match the words or phrases recognized in the recorded speech;
- retrieving a portion of the time-based media program corresponding to the temporal location associated with the selected portion of the script or transcript;
- playing back the retrieved portion of the time-based media program, while the selected portion of the script or transcript and graphical representation of the corresponding confidence levels are displayed, to enable a user to compare the retrieved portion of the time-based media program and the selected portion of the script or transcript;
- and
- in response to input received from the user, making corrections as indicated by the user to the text of the selected portion of the script or transcript, so as to have the corrected text match the words or phrases in the recorded speech, such corrections being made while text from the selected portion of the script or transcript and corresponding graphical representations of the confidence levels are displayed and the corresponding portion of the time-based media is played back.
8 more elements
Dependencies are inferred from the claim text.