/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents syncing voice assistant data when you say a wake word

This filing describes a system where multiple devices with a voice assistant listen for a specific wake word. If the user speaks the wake word, the devices compare who heard it best and then share recent user data over a local connection so the winning device has the latest information to process the request.

Why it mattersIt improves how smart speakers and phones coordinate to ensure the right device responds to your voice with up-to-date personal data.

In the filing’s own words

Techniques are described herein for cross-device data synchronization based on simultaneous hotword triggers. A method includes: executing a first instance of an automated assistant in an inactive state at least in part on a first computing device operated by a user; while in the inactive state, receiving, via one or more microphones of the first computing device, audio data that captures a spoken utterance of the user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a threshold that is indicative of the one or more hotwords being present in the audio data; in response to determining that the predicted output satisfies the threshold, performing arbitration with at least one other computing device that is executing at least in part at least one other instance of the automated assistant; and in response to performing arbitration with the at least one other computing device, initiating synchronization of user data or configuration data between the first instance of the automated assistant on the first computing device and the at least one other instance of the automated assistant on the at least one other computing device, the user data comprising data that is based on one or more interactions with the user at the first computing device, the one or more interactions occurring prior to the receiving of the audio data.

What exactly they claim (claim 1)

1. A method implemented by one or more processors, the method comprising: executing a first instance of an automated assistant in an inactive state at least in part on a first computing device; while in the inactive state, receiving, via one or more microphones of the first computing device, first audio data that captures a spoken utterance of a user; processing the first audio data using a machine learning model to generate a predicted output that indicates a probability of a hotword being present in the first audio data; determining that the predicted output satisfies a threshold indicative of the hotword being present in the first audio data; in response to determining that the predicted output satisfies the threshold, determining that at least a second computing device executing a second instance of the automated assistant concurrently detected the hotword; performing arbitration between the first computing device and the second computing device; based on the arbitration, determining that the first computing device is elected to handle the spoken utterance and that the second computing device is suppressed from handling the spoken utterance; in response to performing the arbitration, initiating a peer-to-peer synchronization to transmit user data from the first computing device to the second computing device over a local communication link; storing the synchronized user data locally on the second computing device; subsequent to the peer-to-peer synchronization, receiving second audio data that captures a subsequent spoken utterance at the second computing device; and utilizing an on-device machine learning model of the second computing device to process the second audio data, wherein the on-device machine learning model processes the second audio data based at least in part on the synchronized user data stored locally on the second computing device.

Facts

Company
Google (GOOGLE LLC)
Official title
CROSS-DEVICE DATA SYNCHRONIZATION BASED ON SIMULTANEOUS HOTWORD TRIGGERS
Publication number
US20260260649A1
Application number
19659625
Filed
Apr 27, 2026
Published
Sep 3, 2026
Inventors
2
Claims
20

Classified under

G10L 15/197 Physics & computingG06F 16/27 Physics & computingG06N 5/043 Physics & computingG06N 20/00 Physics & computingG10L 15/22 Physics & computingG10L 2015/088 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.