View source for US Patent Application 18314643. SYSTEM AND METHOD FOR DEEP AUDIO SPECTRAL PROCESSING FOR RESPIRATION RATE AND DEPTH ESTIMATION USING SMART EARBUDS simplified abstract

=SYSTEM AND METHOD FOR DEEP AUDIO SPECTRAL PROCESSING FOR RESPIRATION RATE AND DEPTH ESTIMATION USING SMART EARBUDS=


==Organization Name==

[[:Category:SAMSUNG ELECTRONICS CO., LTD.|SAMSUNG ELECTRONICS CO., LTD.]]


[[Category:SAMSUNG ELECTRONICS CO., LTD.]]==Inventor(s)==

[[Category:[[:Category:Mohsin Yusuf Ahmed of Sunnyvale CA (US)|Mohsin Yusuf Ahmed of Sunnyvale CA (US)]]]]

[[Category:[[:Category:Tousif Ahmed of San Jose CA (US)|Tousif Ahmed of San Jose CA (US)]]]]

[[Category:[[:Category:Md Mahbubur Rahman of San Jose CA (US)|Md Mahbubur Rahman of San Jose CA (US)]]]]

[[Category:[[:Category:Ebrahim Nematihosseinabadi of San Francisco CA (US)|Ebrahim Nematihosseinabadi of San Francisco CA (US)]]]]

[[Category:[[:Category:Nafiul Rashid of Irvine CA (US)|Nafiul Rashid of Irvine CA (US)]]]]

[[Category:[[:Category:Jilong Kuang of San Jose CA (US)|Jilong Kuang of San Jose CA (US)]]]]

[[Category:[[:Category:Jun Gao of Menlo Park CA (US)|Jun Gao of Menlo Park CA (US)]]]]

==SYSTEM AND METHOD FOR DEEP AUDIO SPECTRAL PROCESSING FOR RESPIRATION RATE AND DEPTH ESTIMATION USING SMART EARBUDS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18314643 titled 'SYSTEM AND METHOD FOR DEEP AUDIO SPECTRAL PROCESSING FOR RESPIRATION RATE AND DEPTH ESTIMATION USING SMART EARBUDS

==Simplified Explanation==

The patent application describes a method for analyzing a user's breathing using earbuds and a convolutional neural network.

* The method involves capturing the user's breathing using earbuds and converting it into a breathing spectrogram image.
* A trained convolutional neural network is then used to process the spectrogram and identify the user's breathing rate and depth.
* The identified breathing rate and depth are then outputted to provide information about the user's breathing patterns.


==Original Abstract Submitted==

A method includes obtaining at least one breathing audio sample of a user captured using earbuds worn by the user. The method also includes converting the at least one breathing audio sample to a breathing spectrogram configured as an image. The method further includes processing the breathing spectrogram using a trained multi-task convolutional neural network (CNN) to identify a breathing rate and a breathing depth of the user. In addition, the method includes outputting the breathing rate and the breathing depth of the user.



[[Category:A61B7/00]]
[[Category:A61B5/00]]
[[Category:A61B5/08]]