18521606. METHOD PERFORMED BY ELECTRONIC DEVICE AND APPARATUS simplified abstract (Samsung Electronics Co., Ltd.)
Contents
- 1 METHOD PERFORMED BY ELECTRONIC DEVICE AND APPARATUS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD PERFORMED BY ELECTRONIC DEVICE AND APPARATUS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
METHOD PERFORMED BY ELECTRONIC DEVICE AND APPARATUS
Organization Name
Inventor(s)
METHOD PERFORMED BY ELECTRONIC DEVICE AND APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18521606 titled 'METHOD PERFORMED BY ELECTRONIC DEVICE AND APPARATUS
Simplified Explanation
The present disclosure describes a method for speech separation in an audio signal, performed by an electronic device.
- Obtaining an audio signal containing a speech signal from at least one sound source.
- Determining a target audio segment based on the speech quality of at least one audio segment.
- Performing speech separation on the audio signal to obtain separated speech signals corresponding to the sound sources.
Potential Applications
This technology can be applied in:
- Speech recognition systems
- Audio editing software
- Teleconferencing tools
Problems Solved
- Enhances speech quality in noisy environments
- Improves the accuracy of speech recognition systems
Benefits
- Clearer audio output
- Better user experience in communication tools
- Increased efficiency in audio processing tasks
Potential Commercial Applications
Optimizing audio quality in:
- Smart speakers
- Virtual assistants
- Video conferencing software
Possible Prior Art
One possible prior art is the use of blind source separation techniques in audio processing to separate mixed audio signals into individual sources.
Unanswered Questions
How does this technology handle overlapping speech signals?
The method described in the abstract focuses on separating speech signals from different sound sources, but it is unclear how it deals with overlapping speech signals from the same source.
What is the computational complexity of this method?
It would be beneficial to know the computational resources required to perform speech separation using this method, especially in real-time applications.
Original Abstract Submitted
The present disclosure provides a method performed by an electronic device and an apparatus. A method performed by an electronic device may include: obtaining an audio signal comprising a speech signal uttered by at least one sound source; determining a target audio segment of the audio signal, wherein the target audio segment is determined based on a speech quality of at least one audio segment, wherein the at least audio segment is divided from the audio signal; and performing speech separation on the audio signal based on the target audio segment to obtain at least one separated speech signal corresponding to the at least one sound source.