Voice detection by multiple devices

Patent metadata

Field	Value
Publication number	US-10152969-B2
Application number	US-201615211748-A
Country	US
Kind code	B2
Filing date	Jul 15, 2016
Priority date	Jul 15, 2016
Publication date	Dec 11, 2018
Grant date	Dec 11, 2018

Abstract

Disclosed herein are example techniques for voice detection by multiple NMDs. An example implementation may involve receiving a set of voice recordings from a set of NMDs, and identifying a subset of voice recordings from which to determine a given voice command. The example implementation may further involve causing the identified subset of voice recordings to be analyzed to determine the given voice command.

First claim

We claim:

1. A first networked microphone device (NMD) comprising:
one or more amplifiers configured to drive one or more speakers;
a microphone array;
a network interface;
one or more processors;
tangible, non-transitory computer-readable media having stored therein instructions executable by the one or more processors to cause the first NMD to perform a method comprising:
continuously recording, via the microphone array, audio into a buffer;
detecting, in the recorded audio, a wake-word;
in response to detecting the wake-word, (i) listening, via the microphone array, for a voice command following the wake-word in the recorded audio and (ii) sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via a local area network, the instructions causing the one or more second NMDs to stop recording audio via respective microphone arrays of the one or more second NMDs for a pre-defined time period;
querying, via the network interface, one or more servers of a particular voice assistant service with the voice command following the detected wake-word within the recorded audio;
receiving, from one or more servers of the particular voice assistant service via the network interface in response to the query, a playback command corresponding to the voice command; and
playing back audio content according to the playback command via the one or more amplifiers configured to drive one or more speakers.

2. The first NMD of claim 1 , wherein the voice command includes an indication of a period of time for the first NMD to listen for the voice command, and wherein the method further comprises sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via the local area network, the instructions causing the one or more second NMDs to stop recording audio via respective microphone arrays of the one or more second NMDs for the period of time indicated by the voice command.

3. The first NMD of claim 2 , wherein the method further comprises:
determining, based on the recorded audio in the buffer, that the first NMD is no longer receiving the voice command, and
based on determining that the first NMD is no longer receiving the voice command, sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via the local area network, the instructions causing the one or more second NMDs to start recording audio via respective microphone arrays of the one or more second NMDs before the period of time indicated by the voice command has fully elapsed.

4. The first NMD of claim 1 , wherein the method further comprises:
determining, based on the recorded audio in the buffer, that the first NMD is no longer receiving the voice command, and
based on determining that the first NMD is no longer receiving the voice command, sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via the local area network, the instructions causing the one or more second NMDs to start recording audio via respective microphone arrays of the one or more second NMDs before the pre-defined time period has fully elapsed.

5. The first NMD of claim 1 , wherein the playback command comprises a command to play back particular audio content in a first zone that includes the first NMD and a second zone that includes a second NMD, and wherein the method further comprises:
instructing, via the network interface, the second NMD of the second zone to play back the audio content according to the playback command in synchrony with playback of the audio content by the first NMD of the first zone.

6. The first NMD of claim 1 , wherein a first zone of a media playback system includes the first NMD, and wherein the first zone is configured into a zone group with a second zone that includes one or more playback devices, and wherein playing back the audio content according to the playback command comprises playing back the audio content in synchrony with one or more playback devices of the second zone.

7. The first NMD of claim 1 , wherein a first zone of a media playback system includes the first NMD and a second NMD in a bonded zone configuration in which the first NMD and the second NMD play respective channels of the audio content, and wherein playing back the audio content according to the playback command comprises playing back a first channel of the audio content in synchrony the second NMD playing back a second channel of the audio content.

8. Tangible, non-transitory, computer-readable media having instructions encoded therein, wherein the instructions, when executed by one or more processors, cause a first networked microphone device (NMD) to perform a method comprising:
continuously recording, via a microphone array of the first NMD, audio into a buffer;
detecting, in the recorded audio, a wake-word;
in response to detecting the wake-word, (i) listening, via a microphone of the first NMD, for a voice command following the wake-word in the recorded audio and (ii) sending, via a network interface, instructions to one or more second NMDs connected via to the first NMD via a local area network, the instructions causing the one or more second NMDs to stop recording audio via respective microphone arrays of the one or more second NMDs for a pre-defined time period;
querying, via a network interface of the first NMD, one or more servers of a particular voice assistant service with the voice command following the detected wake-word within the recorded audio;
receiving, from one or more servers of the particular voice assistant service via the network interface in response to the query, a playback command corresponding to the voice command; and
playing back audio content according to the playback command via one or more amplifiers configured to drive one or more speakers.

9. The tangible, computer readable media of claim 8 , wherein the voice command includes an indication of a period of time for the first NMD to listen for the voice command, and wherein the method further comprises sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via the local area network, the instructions causing the one or more second NMDs to stop recording audio via respective microphone arrays of the one or more second NMDs for the period of time indicated by the voice command.

10. The tangible, computer readable media of claim 9 , wherein the method further comprises:
determining, based on the recorded audio in the buffer, that the first NMD is no longer receiving the voice command, and
based on determining that the first NMD is no longer receiving the voice command, sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via the local area network, the instructions causing the one or more second NMDs to start recording audio via respective microphone arrays of the one or more second NMDs before the period of time indicated by the voice command has fully elapsed.

11. The tangible, computer readable media of claim 8 , wherein the method further comprises:
determining, based on the recorded audio in the buffer, that the first NMD is no longer receiving the voice command, and
based on determining that the first NMD is no longer receiving the voice command, sending, via the network interface, instructions to one or more second NMDs connected via to the first NMD via the local area network, the instructions causing the one or more second NMDs to start recording audio via respective microphone arrays of the one or more second NMDs before the pre-defined time period has fully elapsed.

Assignees

• Sonos Inc

Inventors

• Reilly Jonathon
• Burlingame Gregory
• Butts Christopher
• Kadri Romi
• Lang Jonathan P

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/20

  Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/02

  Feature extraction for speech recognition; Selection of recognition unit · CPC title

• G10L15/34

  Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing · CPC title