Samsung electronics co., ltd. (20240105205). METHOD OF MATCHING SOUND SOURCE FOR EACH OBJECT INCLUDED IN VIDEO, AND COMPUTING DEVICE FOR PERFORMING THE SAME simplified abstract
METHOD OF MATCHING SOUND SOURCE FOR EACH OBJECT INCLUDED IN VIDEO, AND COMPUTING DEVICE FOR PERFORMING THE SAME
Organization Name
Inventor(s)
Hyunkwon Chung of Suwon-si (KR)
Sunghee Hwang of Suwon-si (KR)
METHOD OF MATCHING SOUND SOURCE FOR EACH OBJECT INCLUDED IN VIDEO, AND COMPUTING DEVICE FOR PERFORMING THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240105205 titled 'METHOD OF MATCHING SOUND SOURCE FOR EACH OBJECT INCLUDED IN VIDEO, AND COMPUTING DEVICE FOR PERFORMING THE SAME
Simplified Explanation
The method described in the abstract involves matching voices to objects in a video based on mouth movements. Here is a simplified explanation of the abstract:
- Separating multiple voices in a video
- Calculating the dissimilarity between the voices
- Selecting a matching duration based on the dissimilarity
- Matching voices with objects in the video based on mouth movements
- Extending the matching to the entire duration of the video based on the initial results
- Potential Applications:**
This technology could be used in video editing software to automatically match voices with objects in a scene, making the editing process more efficient and accurate.
- Problems Solved:**
This technology solves the problem of manually matching voices to objects in a video, which can be time-consuming and prone to errors.
- Benefits:**
The benefits of this technology include increased efficiency in video editing, improved accuracy in voice-object matching, and a smoother overall editing process.
- Potential Commercial Applications:**
One potential commercial application of this technology could be in the development of advanced video editing software for professionals in the film and television industry.
- Possible Prior Art:**
One possible prior art could be the use of facial recognition technology in video editing software to match voices with objects based on facial movements.
- Unanswered Questions:**
- 1. How does the technology handle background noise in the video that may interfere with voice-object matching?**
This article does not address how the technology deals with background noise that could potentially affect the accuracy of the voice-object matching process.
- 2. Are there any limitations to the size or complexity of the objects that can be matched with voices using this technology?**
The article does not mention any limitations regarding the size or complexity of objects that can be accurately matched with voices based on mouth movements.
Original Abstract Submitted
a method of matching a voice for each object included in a video, includes: separating a plurality of voices in a video; determining a dissimilarity between the plurality of voices; selecting a partial duration in an entire duration of the video as a matching duration, based on the dissimilarity between the plurality of voices; matching, within the matching duration, the plurality of voices with a plurality of objects in the video respectively, based on mouth movements of the plurality of objects; and matching the plurality of voices with the plurality of objects respectively in the entire duration of the video, based on results of the matching between the plurality of voices and the plurality of objects within the matching duration.
