US 10,297,256 B2Granted

Voice detection by multiple devices

AssigneeSonos, Inc.

InventorsJonathon Reilly, Gregory Burlingame, Christopher Butts, Romi Kadri, Jonathan P. Lang

Life of this patent

Estimating the term…

Loading patent…

Abstract

Disclosed herein are example techniques for voice detection by multiple NMDs. An example implementation may involve one or more servers receiving, via a network interface, data representing multiple audio recordings of a voice input spoken by a given user, each audio recording recorded by a respective NMD of the multiple NMDs, wherein the voice input comprises a detected wake-word. Based on respective sound pressure levels of the multiple audio recordings of the voice input, the servers (i) select a particular NMD of the multiple NMDs and (ii) forego selection of other NMDs of the multiple NMDs. The servers send, via the network interface to the particular NMD, data representing a playback command that corresponds to a voice command in the voice input represented in the multiple audio recordings, wherein the data representing the playback command causes the particular NMD to play back audio content according to the playback command.

Claims21

Dependent claims

A system comprising one or more servers of a voice assistant service, wherein the one or more servers are configured to communicate with multiple network microphone devices, wherein the multiple networked microphone devices (NMDs) are communicatively coupled to one another via a local area network, and wherein:

each NMD is configured to perform operations comprising:
recording, via a respective microphone array, audio into a buffer of the respective NMD;
monitoring the recorded audio for wake-words;
and
when a wake-word is detected in the recorded audio, sending, via a respective network interface to a voice assistant service, data representing an audio recording from the buffer of the respective NMD, the audio recording representing a portion of the recorded audio including the detected wake-word as recorded by the respective NMD;
and
the one or more servers are configured to perform operations comprising:
receiving, via a network interface of the one or more servers, data representing multiple audio recordings of a voice input spoken by a given user, each audio recording recorded by a respective NMD of the multiple NMDs, wherein the voice input comprises the detected wake-word;
based on respective sound pressure levels of the multiple audio recordings of the voice input, (i) selecting a particular NMD of the multiple NMDs and (ii) foregoing selection of other NMDs of the multiple NMDs;
and
after the selecting, sending, via the network interface to the particular NMD, data representing a playback command that corresponds to a voice command following the wake-word in the voice input represented in the multiple audio recordings, wherein the data representing the playback command causes the particular NMD to play back audio content according to the playback command via one or more amplifiers configured to drive one or more speakers.

8 more elements

A method to be performed by one or more servers of a voice assistant service, the method comprising:

receiving, via a network interface of the one or more servers, data representing multiple audio recordings of a voice input spoken by a given user, each audio recording recorded by a respective NMD of multiple networked microphone devices (NMDs) connected via a local area network, wherein the voice input comprises a wake-word detected by the multiple NMDs;
based on respective sound pressure levels of the multiple audio recordings of the voice input, (i) selecting a particular NMD of the multiple NMDs and (ii) foregoing selection of other NMDs of the multiple NMDs;
and
after the selecting, sending, via the network interface to the particular NMD, data representing a playback command that corresponds to a voice command following the wake-word in the voice input represented in the multiple audio recordings, wherein the data representing the playback command causes the particular NMD to play back audio content according to the playback command via one or more amplifiers configured to drive one or more speakers.

1 more element

A method to be performed by a system comprising one or more servers of a voice assistant service, wherein the one or more servers are configured to communicate with multiple network microphone devices, wherein the multiple networked microphone devices (NMDs) are communicatively coupled to one another via a local area network, and wherein:

each NMD is configured to perform operations comprising:
recording, via a respective microphone array, audio into a buffer of the respective NMD;
monitoring the recorded audio for wake-words;
and
when a wake-word is detected in the recorded audio, sending, via a respective network interface to a voice assistant service, data representing an audio recording from the buffer of the respective NMD, the audio recording representing a portion of the recorded audio including the detected wake-word as recorded by the respective NMD;
and
the method comprises:
receiving, via a network interface of the one or more servers, data representing multiple audio recordings of a voice input spoken by a given user, each audio recording recorded by a respective NMD of the multiple NMDs, wherein the voice input comprises the detected wake-word;
based on respective sound pressure levels of the multiple audio recordings of the voice input, (i) selecting a particular NMD of the multiple NMDs and (ii) foregoing selection of other NMDs of the multiple NMDs;
and
after the selecting, sending, via the network interface to the particular NMD, data representing a playback command that corresponds to a voice command following the wake-word in the voice input represented in the multiple audio recordings, wherein the data representing the playback command causes the particular NMD to play back audio content according to the playback command via one or more amplifiers configured to drive one or more speakers.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/214,666Filed 10 Dec 2018 · continuation
Priority: 15 Jul 2016
Published: US 2019/0108839 A111 Apr 2019
Granted: 21 May 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G06F 3/167
Sound input; Sound output: audio in a user interface, e.g. using voice commands for navigating, audio feedback
G10L 15/02
Speech recognition: feature extraction for speech recognition; Selection of recognition unit
G10L 15/20
Speech recognition: speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech

Family

Application15/211,748Parent of this continuation · filed 15 Jul 2016
US 2019/0108839 A1Pre-grant publication · published 11 Apr 2019
US 10,152,969 B2Parent of this continuation
US 2018/0018964 A1Published application
US 10,297,256 B2This patent

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