The present disclosure describes systems and methods that can determine a context of an audible query based at least in part on a source and/or a source location of the query. More particularly, the present disclosure enables a computing system, and methods for controlling the same, to determine a source location of an audible query, identify a source (e.g., a user/speaker) of the audible query, and determine a context for the audible query based in part on a subject of an attention of the source. The computing system can user the determined context to improve a response to the audible query. Keywords associated with the present disclosure include: computing systems (e.g., smartphone, smartwatch, mobile phone, automated assistant, home assistant, personal assistant); user; multiple users; hotword; query; context; context-aware; localization; triangulation; facial recognition; object tracking.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Raphael, Seth, "Systems and Methods for Identifying a Speaker and/or Their Attention with Cameras and/or Microphones", Technical Disclosure Commons, (April 16, 2018)