18335730. THREE-DIMENSIONAL (3D) SOUND RENDERING WITH MULTI-CHANNEL AUDIO BASED ON MONO AUDIO INPUT simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
THREE-DIMENSIONAL (3D) SOUND RENDERING WITH MULTI-CHANNEL AUDIO BASED ON MONO AUDIO INPUT
Organization Name
Inventor(s)
Vijendra Raj Apsingekar of San Jose CA (US)
Akash Sahoo of San Jose CA (US)
Anil S. Yadav of San Jose CA (US)
Sivakumar Balasubramanian of Sunnyvale CA (US)
THREE-DIMENSIONAL (3D) SOUND RENDERING WITH MULTI-CHANNEL AUDIO BASED ON MONO AUDIO INPUT - A simplified explanation of the abstract
This abstract first appeared for US patent application 18335730 titled 'THREE-DIMENSIONAL (3D) SOUND RENDERING WITH MULTI-CHANNEL AUDIO BASED ON MONO AUDIO INPUT
Simplified Explanation
The method involves analyzing video content and associated mono audio content to determine the position or motion trajectory of objects detected in the video and classify them into different object classes. The audio streams are separated based on the video content and classified into different audio sources, which are then further classified into object classes. The audio streams associated with each object are distributed into multiple audio channels based on the position or motion trajectory of that object.
- Analyzing video content and mono audio content
- Determining position or motion trajectory of objects in the video
- Classifying objects into different object classes
- Separating audio streams based on video content
- Classifying audio sources into object classes
- Distributing audio streams into multiple channels based on object position or motion trajectory
- Potential Applications
- Audio enhancement in video content
- Virtual reality and augmented reality applications
- Object tracking and identification in videos
- Problems Solved
- Enhancing audio experience in videos
- Improving object recognition and classification in videos
- Benefits
- Enhanced audio quality
- Improved object tracking and classification
- Better user experience in virtual and augmented reality applications
Original Abstract Submitted
A method includes obtaining video content and associated substantially mono audio content. The method also includes determining at least one of a position or a motion trajectory of each of one or more objects detected in the video content and classifying each of the one or more objects into one of multiple object classes. The method further includes separating audio streams within the audio content based on the video content. Each of the audio streams is associated with one of multiple audio sources. The method also includes classifying each of the audio sources into one of the object classes. In addition, the method includes, for each audio source classified into the same object class as one of the one or more objects, distributing the audio stream associated with that audio source into multiple audio channels based on at least one of the position or the motion trajectory of that object.
