Automatic appending of subtitles based on media context
AssigneeInternational Business Machines Corporation
InventorsJian Dong Yin, Wen Wang, Zhuo Cai, Rong Fu, Hao Sheng, Kang Zhang
Life of this patent
Estimating the term…
Abstract
A processor may automatically generate one or more transcripts based on a media context. The processor may append at least one of the one or more transcripts to the media. The processor may modify the at least one of the one or more transcripts based on an adjustment to a weight factor.
Claims20
A system for automatically appending additional transcription in a media, the system comprising:
- a memory;
- and
- a processor in communication with the memory, the processor being configured to perform operations comprising:
- extract dialog from a video fragment, wherein dialog is human voices;
- determine one or more quality features from the extracted dialog;
- identify a tone of the dialog based on the one or more quality features;
- generate, automatically, one or more transcripts based on a media context, wherein the one or more transcripts are not a part of an existing transcript of the media;
- append at least one of the one or more transcripts to the media, wherein appending the at least one of the one or more transcripts to the media includes relaying a mood associated with the identified tone of the dialog;
- and
- modify the at least one of the one or more transcripts based on an adjustment to a weight factor.
A computer-implemented method for automatically appending additional transcription in a media, the method comprising:
- extracting dialog from a video fragment, wherein dialog is human voices;
- determining one or more quality features from the extracted dialog;
- identifying a tone of the dialog based on the one or more quality features;
- generating, automatically, one or more transcripts based on a media context, wherein the one or more transcripts are not a part of an existing transcript of the media;
- appending at least one of the one or more transcripts to the media, wherein appending the at least one of the one or more transcripts to the media includes relaying a mood associated with the identified tone of the dialog;
- and
- modifying the at least one of the one or more transcripts based on an adjustment to a weight factor.
A computer program product for automatically appending additional transcription in a media comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations, the operations comprising:
- extract dialog from a video fragment, wherein dialog is human voices;
- determine one or more quality features from the extracted dialog;
- identify a tone of the dialog based on the one or more quality features;
- generate, automatically, one or more transcripts based on a media context, wherein the one or more transcripts are not a part of an existing transcript of the media;
- append at least one of the one or more transcripts to the media, wherein appending the at least one of the one or more transcripts to the media includes relaying a mood associated with the identified tone of the dialog;
- and
- modify the at least one of the one or more transcripts based on an adjustment to a weight factor.
Dependencies are inferred from the claim text.