Editing multimedia contents based on voice recognition
AssigneeLG Electronics Inc.
InventorSeunghyun Kim
Life of this patent
Estimating the term…
Abstract
Disclosed are a content editing apparatus and method capable of editing a video filmed by a personal terminal in a 5G communication environment. The content editing apparatus of the present disclosure includes a processor, a memory operatively connected to the processor and which stores at least one code configured to be executed by the processor, and an interface for receiving a video. The memory stores codes that, when executed by the processor, cause the processor to recognize a set wake-up word from the video, and edit the video based on an editing command recognized within an interval of a preset time from a portion where the wake-up word of the video is located.
Claims17
A content editing apparatus comprising:
- a processor;
- a memory operatively connected to the processor, the memory storing at least one code configured to be executed by the processor;
- and
- an interface configured to receive a video,
- wherein the memory stores a code configured to, when executed by the processor, cause the processor to:
- recognize a set wake-up word from the video;
- and
- edit the video based on an editing command recognized within an interval of a preset time from a portion where the wake-up word of the video is located;
- and
- wherein the editing includes:
- determining a category of the video;
- comparing each scene of the video with each scene of a template corresponding to the category of the video;
- and
- inserting into the video at least some scenes that do not correspond to the scenes of the video among the scenes of the template.
A method for editing content, performed by a content editing apparatus comprising a processor, the method comprising:
- receiving a video, by an interface of the content editing apparatus;
- recognizing, by the processor, a set wake-up word from the video;
- and
- editing, by the processor, the video based on an editing command recognized within an interval of a preset time from a portion where the wake-up word of the video is located,
- wherein the editing of the video comprises determining a category of the video, comparing each scene of the video with each scene of a template corresponding to the category of the video, and inserting into the video at least some scenes of the template that do not correspond to the scenes of the video.
Dependencies are inferred from the claim text.