US 2026/0237387 A1Published application

Voice assistant persistence across multiple network microphone devices

AssigneeSonos, Inc.

InventorsConnor Kristopher Smith, Paul Bates

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods for maintaining voice assistant persistence across multiple network microphone devices are described. In one example, first and second NMDs each identify a wake word based on detected sound, and are each transitioned from an inactive state to an active state in which the NMD captures and transmits sound data over a network interface. The first NMD is selected over the second NMD to output a first response, and both NMDs remain in the active state to further capture and transmit sound data. After further capturing and transmitting of sound data, the second NMD is selected over the first NMD to output a second response. After a predetermined time, one or both of the NMDs are transitioned back to the inactive state. The selection of one NMD over another for outputting a response can be based at least in part on user location information.

Claims20

Dependent claims

A media playback system including at least a first network microphone device (NMD) and a second NMD, the media playback system comprising:

one or more processors;
and
data storage having instructions stored thereon that, when executed by the one or more processors, cause the media playback system to perform operations comprising:
detecting, via the first NMD, a voice input from a user, the voice input comprising a wake word associated with a voice assistant service (VAS);
transitioning the first NMD from an inactive state to an active state in which the first NMD captures sound data and transmits the sound data over a network interface;
during a first portion of a multi-turn conversation between the user and the VAS, receiving a first response from the VAS and outputting the first response via the first NMD;
determining that the user has moved from a first location proximate the first NMD to a second location proximate the second NMD;
transitioning the second NMD to an active state in which the second NMD captures sound data and transmits the sound data over a network interface;
and
during a second portion of the multi-turn conversation, capturing a subsequent voice input from the user via the second NMD and outputting a second response from the VAS via the second,
wherein the first portion and the second portion are part of a continuous conversational session with the VAS.

8 more elements

A method performed by a media playback system comprising a first network microphone device (NMD) and a second NMD, the method comprising:

detecting, via the first NMD, a voice input from a user, the voice input comprising a wake word associated with a voice assistant service (VAS);
transitioning the first NMD from an inactive state to an active state in which the first NMD captures sound data and transmits the sound data over a network interface;
during a first portion of a multi-turn conversation between the user and the VAS, receiving a first response from the VAS and outputting the first response via the first NMD;
determining that the user has moved from a first location proximate the first NMD to a second location proximate the second NMD;
transitioning the second NMD to an active state in which the second NMD captures sound data and transmits the sound data over a network interface;
and
during a second portion of the multi-turn conversation, capturing a subsequent voice input from the user via the second NMD and outputting a second response from the VAS via the second,
wherein the first portion and the second portion are part of a continuous conversational session with the VAS.

5 more elements

One or more tangible, non-transitory, computer-readable media having stored therein instructions executable by one or more processors to cause a media playback system comprising first and second network microphone devices (NMDs) to perform operations comprising:

detecting, via the first NMD, a voice input from a user, the voice input comprising a wake word associated with a voice assistant service (VAS);
transitioning the first NMD from an inactive state to an active state in which the first NMD captures sound data and transmits the sound data over a network interface;
during a first portion of a multi-turn conversation between the user and the VAS, receiving a first response from the VAS and outputting the first response via the first NMD;
determining that the user has moved from a first location proximate the first NMD to a second location proximate the second NMD;
transitioning the second NMD to an active state in which the second NMD captures sound data and transmits the sound data over a network interface;
and
during a second portion of the multi-turn conversation, capturing a subsequent voice input from the user via the second NMD and outputting a second response from the VAS via the second NMD,
wherein the first portion and the second portion are part of a continuous conversational session with the VAS.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 19/408,105Filed 3 Dec 2025
Priority: 3 May 2019
Published: 13 Aug 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G10L 15/08
Speech recognition: speech classification or search
G10L 15/32
Constructional details of speech recognition systems: multiple recognisers used in sequence or in parallel; Score combination systems therefor,…
H04R 1/326
For obtaining desired directional characteristic only: for microphones

Family

Application16/402,617Continuation · filed 3 May 2019
Application17/305,920Continuation · filed 16 Jul 2021
Application18/461,430Continuation · filed 5 Sep 2023
Application19/408,105Continuation
US 11,120,794 B2Related patent
US 11,798,553 B2Related patent
US 12,518,756 B2Related patent
US 2020/0349935 A1Published application
US 2021/0343285 A1Published application
US 2023/0410813 A1Published application
US 2026/0237387 A1This patent

From the US filing history. Foreign family members aren’t listed.