Detecting and measuring snoring
Inventors
Su, Hao-Wei • Niehaus, Logan Alexander • Heneghan, Conor Joseph • Charlesworth, Jonathan David • Venkatraman, Subramaniam • Yuen, Shelten Gee Jao
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12201442-B2
Publication Date
2025-01-21
Expiration Date
Abstract
Approaches described herein can capture an audio signal using at least one microphone while a user of an electronic device is determined to be asleep. At least one audio frame can be determined from the audio signal. The at least one audio frame represents a spectrum of frequencies detected by the at least one microphone over some period of time. One or more sounds associated with the at least one audio frame can be determined. Sleep-related information can be generated. The information identifies the one or more sounds as potential sources of sleep disruption.
Core Innovation
The invention relates to wearable-system detection of snoring by capturing microphone audio while a user is determined to be asleep. A breathing phase pattern determined for the user governs activating and deactivating at least one microphone, and audio frames of the captured audio signal are analyzed during the microphone-activated periods. The system determines whether an audio frame includes one or more sounds indicative of snoring.
When an audio frame includes one or more sounds indicative of snoring, the system discards the audio frame. Sleep-related information is generated that identifies the one or more sounds as an instance of snoring. The approach includes privacy-by-design frame discarding for real-time operation, as described in the partial content.
The described sleep-related information is expanded with snoring-duration and intensity metrics, including quantitative snoring-time measures and correlations based on detected snoring-associated sounds. The system architecture supports wearable and remote processing, and provides presentation of snoring outcomes through interfaces such as snore reports and graphs.
Claims Coverage
The independent claims are clm-00001 (computing system) and clm-00014 (method). Each independent claim is organized around four inventive features: breathing-phase-pattern-controlled microphone activation/deactivation, audio-frame determination for snoring-indicative sounds, discarding snoring-relevant frames, and generating sleep-related information identifying the snoring instance.
Breathing phase pattern controls microphone activation and deactivation
Activating and deactivating at least one microphone according to a breathing phase pattern determined for a user that is determined to be asleep.
Snoring-indicative sound detection in audio frames
Determining an audio frame of the audio signal includes one or more sounds indicative of snoring.
Discarding snoring-indicative audio frames
In response to determining the audio frame includes the one or more sounds indicative of snoring, discarding the audio frame.
Sleep-related information identifying snoring instances
Generating sleep-related information that identifies the one or more sounds as an instance of snoring.
Together, the independent claims cover a computing system and a corresponding method that use a breathing phase pattern for a user determined to be asleep to control microphone activation, determine snoring-indicative sounds within audio frames, discard those frames when snoring-indicative sounds are determined, and generate sleep-related information identifying the snoring instances.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Wearable-system snoring detection while a user is determined to be asleep, including generation of sleep-related information identifying snoring instances and associated snoring metrics.
Privacy-by-design real-time processing through discarding analyzed audio frames after identification.
User-facing presentation of snoring outcomes via snore reports and graphs, including expanded analytics such as snoring metrics and correlations between awake periods and potential sleep disruption sounds.
Interested in licensing this patent?