SK Telecom Co., Ltd. (20240265932). DEVICE AND METHOD FOR AUTOMATICALLY REMOVING A BACKGROUND SOUND SOURCE OF A VIDEO simplified abstract
Contents
DEVICE AND METHOD FOR AUTOMATICALLY REMOVING A BACKGROUND SOUND SOURCE OF A VIDEO
Organization Name
Inventor(s)
DEVICE AND METHOD FOR AUTOMATICALLY REMOVING A BACKGROUND SOUND SOURCE OF A VIDEO - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240265932 titled 'DEVICE AND METHOD FOR AUTOMATICALLY REMOVING A BACKGROUND SOUND SOURCE OF A VIDEO
The present disclosure describes a method for automatically removing background sound sources from audio data in a video by separating the audio data into different components related to human voice, speech, music, and noise.
- Separation of audio data into components related to human voice and other sounds using different separation models.
- Further separation of the human voice component into vocal and speech components.
- Separation of the non-human voice component into music and noise components.
- Generation of audio data with the background sound source removed by synthesizing the speech and noise components.
Potential Applications: - Video editing software for removing unwanted background noise. - Improving audio quality in videos for better user experience. - Enhancing speech clarity in recorded videos.
Problems Solved: - Eliminating distracting background noise from audio data. - Enhancing the overall audio quality of videos. - Improving the intelligibility of human speech in videos.
Benefits: - Enhanced user experience with clearer audio in videos. - Increased professional quality of video content. - Simplified process for removing background sound sources.
Commercial Applications: Title: Automatic Background Sound Removal Technology for Video Editing This technology can be used in: - Film and video production studios - Content creation platforms - Online video editing tools
Questions about the Technology: 1. How does this technology compare to manual methods of removing background sound sources in videos? - This technology offers a more efficient and automated solution compared to manual editing processes, saving time and effort. 2. Can this technology be applied to live audio recordings or is it limited to pre-recorded videos? - This technology is primarily designed for pre-recorded videos but could potentially be adapted for live audio processing in the future.
Original Abstract Submitted
one aspect of the present disclosure provides a method for automatically removing a background sound source of audio data of a video, including separating the audio data including at least one sound source component into a first component related to a human voice and a second component related to sounds other than the human voice using a first separation model, separating the first component into a vocal component and a speech component using a second separation model, separating the second component into a music component and a noise component using a third separation model, and generating an audio data with the background sound source for the audio data of the video removed by synthesizing the speech component and the noise component.