20240029754. AUDIO SOURCE SEPARATION FOR AUDIO DEVICES simplified abstract (Apple Inc.)
Contents
AUDIO SOURCE SEPARATION FOR AUDIO DEVICES
Organization Name
Inventor(s)
Carlos M. Avendano of Campbell CA (US)
John Woodruff of Santa Cruz CA (US)
Jonathan Huang of Pleasanton CA (US)
Mehrez Souden of Los Angeles CA (US)
Andreas Koutrouvelis of Cupertino CA (US)
AUDIO SOURCE SEPARATION FOR AUDIO DEVICES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240029754 titled 'AUDIO SOURCE SEPARATION FOR AUDIO DEVICES
Simplified Explanation
The subject technology provides systems and methods for audio source separation for audio input, particularly for audio devices with limited power and computing resources. It allows an audio device to utilize the processing and power resources of a companion device that is connected to it. The companion device identifies the noise condition of the audio device, selects a source separation model based on the noise condition, and provides the model to the audio device. This enables the audio device to perform audio source separation using a small footprint model specific to its noise condition.
- The technology enables audio devices with limited power and computing resources to perform audio source separation.
- It leverages the processing and power resources of a companion device that is connected to the audio device.
- The companion device identifies the noise condition of the audio device.
- Based on the noise condition, a suitable source separation model is selected.
- The selected model is provided to the audio device for performing audio source separation.
- This approach allows the audio device to use a small footprint model specific to its noise condition, resulting in efficient processing.
Potential Applications
- Audio devices with limited power and computing resources can benefit from this technology.
- It can be used in smartphones, tablets, or other portable devices to enhance audio quality.
- Communication devices, such as headsets or conference systems, can utilize this technology for improved audio separation.
Problems Solved
- Limited power and computing resources of audio devices can restrict their ability to perform complex audio processing tasks.
- Audio source separation requires significant processing resources, which may not be available in certain devices.
- Using a small footprint model specific to the noise condition solves the problem of resource limitations and allows efficient audio source separation.
Benefits
- Improved audio quality and separation for audio devices with limited resources.
- Efficient utilization of processing and power resources by leveraging a companion device.
- Customized source separation models for different noise conditions, resulting in accurate separation.
Original Abstract Submitted
implementations of the subject technology provide systems and methods for providing audio source separation for audio input, such as for audio devices having limited power and/or computing resources. the subject technology may allow an audio device to leverage processing and/or power resources of a companion device that is communicatively coupled to the audio device. the companion device may identify a noise condition of the audio device, select a source separation model based on the noise condition, and provide the source separation model to the audio device. in this way, the audio device can provide audio source separation functionality using a relatively small footprint source separation model that is specific to the noise condition in which the audio device is operated.
