Generating and/or Displaying Synchronized Captions
AssigneeComcast Cable Communications, LLC
InventorRoss Gilson
Life of this patent
Estimating the term…
Abstract
Methods, apparatuses, and systems are described for correlating automatically-generated timing information from a first audio transcript with a second audio transcript (such as a transcript generated by one or more human transcribers) that may not have timing information. By correlating the second transcript with the timing information, an accurate and synchronized transcript may be generated. To correlate the second transcript with the timing information, a first transcript that contains the timing information may be automatically generated, and words of the first transcript may be compared to words of the second transcript. Based on the comparison, the timing information of the first transcript can be associated with the words of the second transcript.
Claims20
A method comprising:
- generating a first transcript of an audio portion of media content, wherein the first transcript comprises time codes synchronizing first words of the first transcript with the media content;
- correlating the first words of the first transcript with second words of a second transcript of the audio portion;
- generating, based on the time codes and on the correlating, caption data;
- and
- transmitting the media content and the caption data.
A method comprising:
- generating a first transcript of an audio portion of media content, wherein the first transcript comprises time codes synchronizing first words of the first transcript with the media content;
- generating, based on an output of a transcriber device, a second transcript of the audio portion;
- generating, based on first transcript and the second transcript, caption data;
- and
- transmitting the media content and the caption data.
A system comprising:
- a sending device comprising:
- one or more first processors;
- and
- first memory storing first instructions that, when executed by the one or more first processors, cause the sending device to:
- generate a first transcript of an audio portion of media content, wherein the first transcript comprises time codes synchronizing first words of the first transcript with the media content;
- correlate the first words of the first transcript with second words of a second transcript of the audio portion;
- generate, based on the time codes and on the correlation, caption data;
- and
- transmit the media content and the caption data;
- and,
- a receiving device comprising:
- one or more second processors;
- and
- second memory storing second instructions that, when executed by the one or more second processors, cause the receiving device to display the media content and captions of the caption data.
Dependencies are inferred from the claim text.