US 11,887,581 B2
Automatic audio playback of displayed textual content
Rachel Ilan Simpson, London (GB); Benedict Davies, London (GB); and Guillaume Boniface-Chang, London (GB)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 17/052,046
Filed by Google LLC, Mountain View, CA (US); Rachel Ilan Simpson, London (GB); Benedict Davies, London (GB); and Guillaume Boniface-Chang, London (GB)
PCT Filed Nov. 14, 2019, PCT No. PCT/US2019/061401
§ 371(c)(1), (2) Date Oct. 30, 2020,
PCT Pub. No. WO2021/096507, PCT Pub. Date May 20, 2021.
Prior Publication US 2023/0094174 A1, Mar. 30, 2023
Int. Cl. G06F 3/04883 (2022.01); G10L 13/08 (2013.01); G06F 3/0485 (2022.01); G10L 13/02 (2013.01)
CPC G10L 13/08 (2013.01) [G06F 3/0485 (2013.01); G10L 13/02 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method to perform audio playback of displayed textual content, the method comprising:
obtaining, by one or more computing devices, data descriptive of one or more items of content that include a plurality of portions of textual content;
determining, by the one or more computing devices, positional data that indicates respective positions of one or more of the portions of textual content on a display associated with the one or more computing devices;
receiving, by the one or more computing devices, data indicative of a user input that modifies the respective positions of the one or more of the portions of textual content relative to the display; and
responsive to receiving the data indicative of the user input:
determining, by the one or more computing devices, updated positional data that indicates respective updated positions of the one or more of the portions of textual content;
identifying, by the one or more computing devices and based at least in part on the updated positional data, that a first portion of textual content is positioned within a playback area of the display; and
causing, by the one or more computing devices, playback of an audio signal that includes speech of at least a portion of the first portion of textual content, wherein the speech of at least a portion of the first portion of textual content is determined at least in part using a trained machine learned model.