View source for US Patent Application 17804722. LEVERAGING VISUAL DATA TO ENHANCE AUDIO RECEPTION simplified abstract

=LEVERAGING VISUAL DATA TO ENHANCE AUDIO RECEPTION=


==Organization Name==

[[:Category:AT&T Intellectual Property I, L.P.|AT&T Intellectual Property I, L.P.]]


[[Category:AT&T Intellectual Property I, L.P.]]

==Inventor(s)==

[[:Category:Zachary Cleigh Meredith of Eagle River AK (US)|Zachary Cleigh Meredith of Eagle River AK (US)]][[Category:Zachary Cleigh Meredith of Eagle River AK (US)]]

[[:Category:Peter Hardie of Cumming GA (US)|Peter Hardie of Cumming GA (US)]][[Category:Peter Hardie of Cumming GA (US)]]

[[:Category:Sheldon Kent Meredith of Roswell GA (US)|Sheldon Kent Meredith of Roswell GA (US)]][[Category:Sheldon Kent Meredith of Roswell GA (US)]]

==LEVERAGING VISUAL DATA TO ENHANCE AUDIO RECEPTION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17804722 titled 'LEVERAGING VISUAL DATA TO ENHANCE AUDIO RECEPTION

==Simplified Explanation==

The patent application describes a method for improving audio quality in a captured audio stream by using visual data to infer the sound being made by the source of the audio stream.

* The method calculates the signal to noise ratio of the captured audio stream.
* If the signal to noise ratio is below a predefined threshold, visual data of the source of the audio stream is acquired.
* The visual data is then used to infer the sound being made by the source of the audio stream.
* The inferred sound is indexed to a library index.
* Finally, the library index is transferred to a receiving user endpoint device.


==Original Abstract Submitted==

In one example, a method includes calculating a signal to noise ratio of a captured audio stream, determining that the signal to noise ratio of the captured audio stream is lower than a predefined threshold, acquiring visual data of a source of the captured audio stream in response to the determining that the signal to noise ratio of the captured audio stream is lower than the predefined threshold, using the visual data to infer a sound that is being made by the source of the captured audio stream, indexing the sound that is being made by the source of the captured audio stream to a library index, and transferring the library index to a receiving user endpoint device.



[[Category:G06F3/16]]
[[Category:G10K11/178]]