| CPC G10L 15/22 (2013.01) [G06F 3/0482 (2013.01); G06F 3/167 (2013.01); G10L 15/063 (2013.01); G10L 15/1815 (2013.01); G10L 15/26 (2013.01); G10L 2015/0638 (2013.01); G10L 2015/223 (2013.01)] | 20 Claims |

|
1. A device comprising:
a microphone;
a processor; and
a memory storing instructions that, upon execution by the processor, configure the device to:
present content on a display;
detect, by at least using the microphone, a natural language input requesting an operation associated with at least a portion of the content;
generate data that represents the natural language input;
generate an input to a language model based at least in part on the data and whether the content is in view or out of view;
determine, based at least in part on the input, an output of the language model, wherein the output indicates a command to perform and is based at least in part on the data and whether the content is in view or out of view; and
present, on the display, an outcome of performing the command.
|