18105046. METHOD FOR PROCESSING VOICE SIGNAL, AND APPARATUS USING SAME simplified abstract (Samsung Electronics Co., Ltd.)
Jump to navigation
Jump to search
METHOD FOR PROCESSING VOICE SIGNAL, AND APPARATUS USING SAME
Organization Name
Inventor(s)
METHOD FOR PROCESSING VOICE SIGNAL, AND APPARATUS USING SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 18105046 titled 'METHOD FOR PROCESSING VOICE SIGNAL, AND APPARATUS USING SAME
Simplified Explanation
The abstract describes an audio apparatus that includes a sensor, multiple microphones, and a processor. The processor is configured to obtain a speech presence probability from a sensor signal and use it to cancel noise from a speech signal received from the microphones.
- The audio apparatus includes a sensor, multiple microphones, and a processor.
- The processor obtains a speech presence probability from a sensor signal.
- The obtained speech presence probability is used to cancel noise from a speech signal received from the microphones.
Potential Applications
- Speech enhancement in noisy environments
- Improved audio quality in teleconferencing systems
- Noise cancellation in voice recognition systems
Problems Solved
- Reduction of background noise in speech signals
- Improved accuracy of speech recognition in noisy environments
- Enhanced audio experience in various applications
Benefits
- Clearer and more intelligible speech in noisy environments
- Improved performance of voice-controlled devices
- Enhanced user experience in audio communication systems
Original Abstract Submitted
An audio apparatus includes: a sensor; a plurality of microphones; and at least one processor configured to: obtain a speech presence probability from a sensor signal obtained using the sensor; and cancel, using the obtained speech presence probability, noise from a speech signal received from at least one of the plurality of microphones.