/Patent Tracker
GoogleGranted patentAudio & voiceInterest 6/10

Google patents method for smart speakers to decide who answers

This patent describes a system where multiple voice assistant devices in a home listen to the same command. The devices compare their own status and how relevant the command is to them, then only the best-suited device responds to avoid confusion.

Why it mattersThis helps prevent multiple smart speakers from talking over each other, making voice interactions smoother for users with several devices in one room.

In the filing’s own words

The various implementations described herein include methods and systems for determining device leadership among voice interface devices. In one aspect, a method is performed at a first electronic device of a plurality of electronic devices, each having microphones, a speaker, processors, and memory storing programs for execution by the processors. The first device detects a voice input. It determines a device state and a relevance of the voice input. It identifies a subset of electronic devices from the plurality to which the voice input is relevant. In accordance with a determination that the subset includes the first device, the first device determines a first score of a criterion associated with the voice input and receives second scores of the criterion from other devices in the subset. In accordance with a determination that the first score is higher than the second scores, the first device responds to the detected input.

What exactly they claim (claim 1)

1. A computer-implemented method when executed on data processing hardware of a first voice assistant device causes the data processing hardware to perform operations comprising: receiving a voice input comprising a hotword and a voice request subsequent to the hotword, the voice input captured by the first voice assistant device and a second voice assistant device, the first voice assistant device and the second voice assistant device each communicatively coupled to a local network implemented at a network interface and configured to respond to voice requests that are subsequent to the hotword; detecting, in the voice input, the hotword; based on detecting the hotword, processing the voice input to determine that the voice request comprises a media play request to playback media content on a media output device; sending, from the first voice assistant device via the local network, a multicast message received by the second voice assistant device, the multicast message received by the second voice assistant device causing the second voice assistant device to not respond to the voice request despite the second voice assistant device capturing the voice input of the hotword and the voice request subsequent to the hotword; and based on determining that voice request comprises the request to playback the media content on the media output device, causing the media output device to playback the media content.

Facts

Company
Google (Google LLC)
Official title
Device leadership negotiation among voice interface devices
Patent number
US12749485B2
Application number
18766909
Filed
Jul 9, 2024
Granted
Sep 29, 2026
Inventors
6
Claims
20

Classified under

G10L 15/22 Physics & computingG10L 15/32 Physics & computingG10L 2015/088 Physics & computingG10L 2015/223 Physics & computingG10L 25/60 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in Audio & voice

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.