Wake-word detection suppression

• US 10,475,449 B2
• Filed: 08/07/2017
• Issued: 11/12/2019
• Est. Priority Date: 08/07/2017
• Status: Active Grant

• Current Assignee: Sonos, Inc.
• Original Assignee: Sonos, Inc.
• Inventors: Lang, Jonathan P.
• Primary Examiner(s): Albertalli, Brian L
• Application Number:
  US15/670,361
• Publication Number:
  US 20190043492A1
• Time in Patent Office: 827 Days
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone

Abstract

Example techniques involve determining a direction of a NMD. An example implementation includes a playback device receiving data representing audio content for playback by the playback device. Before the audio content is played back by the playback device, the playback device detects, in the audio content, one or more wake words for one or more voice services. The playback device causes one or more networked microphone devices to disable its respective wake response to the detected one or more wake words during playback of the audio content by the playback device and plays back the audio content via one or more speakers. When enabled, the wake response of a given networked microphone device to a particular wake word causes the given networked microphone device to listen, via a microphone, for a voice command following the particular wake word.

Claims

1. A playback device comprising:

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 playback device to perform operations comprising;

receiving, via the network interface, data representing audio content for playback by the playback device;

before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services;

causing one or more networked microphone devices to disable its respective wake response to the detected one or more wake words during playback of the audio content by the playback device, wherein, when enabled, the wake response of a given networked microphone device to a particular wake word causes the given networked microphone device to listen, via a microphone, for a voice command following the particular wake word, wherein the one or more networked microphones devices are a subset of networked microphone devices in a household, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises;

determining that the one or more networked microphone devices are in audible vicinity of the audio content; and

in response to determining that the one or more networked microphones are in audible vicinity of the audio content, sending, via the network interface to the one or more networked microphone devices, instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device; and

playing back the audio content via one or more speakers.

2. The playback device of claim 1, wherein the playback device comprises the given networked microphone device, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

while playing back the audio content, recording, via the microphone, the audio content being played back; and

disabling respective wake responses of the given networked microphone device to the one or more wake words within the recorded audio content.

3. The playback device of claim 1, wherein the one or more networked microphone devices comprise respective playback devices, and wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in a synchronous playback configuration with the playback device.

4. The playback device of claim 1, wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in audible vicinity of the playback device.

5. The playback device of claim 1, wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

before playing back the audio content, modifying the audio content to incorporate acoustic markers in segments of the audio content that represent respective wake words, wherein detecting the acoustic markers causes the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

6. The playback device of claim 1, wherein detecting the one or more wake words comprises applying multiple wake-word detection algorithms to the audio content, wherein the multiple wake-word detection algorithms comprise a first wake-word detection algorithm for a first voice service and a second wake-word detection algorithm for a second voice service, and wherein applying multiple wake-word detection algorithms to the audio content before the audio content is played back by the playback device comprises:

applying, to the audio content before the audio content is played back by the playback device, the first wake-word detection algorithm for the first voice service to detect at least one first wake word for the first voice service; and

applying, to the audio content before the audio content is played back by the playback device, the second wake-word detection algorithm for the second voice service to detect at least one second wake word for the second voice service, wherein the second wake word is a different word than the first wake word.

7. The playback device of claim 6, wherein the one or more networked microphone devices comprise a first networked microphone device and a second networked microphone device, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

causing the first networked microphone device to disable its respective wake response to the detected at least one first wake word; and

causing the second networked microphone device to disable its respective wake response to the detected at least one second wake word.

8. The playback device of claim 1, wherein detecting, in the audio content, one or more wake words for one or more voice services comprises detecting multiple instances of a particular wake word in the audio content, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises causing the one or more networked microphone devices to disable their respective wake responses until each networked microphone device has detected a number of wake words equal to a number of the multiple instances of the particular wake word detected in the audio content.

9. A tangible, non-transitory, computer-readable media having stored therein instructions executable by one or more processors to cause a playback device to perform operations comprising:

receiving, via a network interface, data representing audio content for playback by the playback device;

before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services;

causing one or more networked microphone devices to disable its respective wake response to the detected one or more wake words during playback of the audio content by the playback device, wherein, when enabled, the wake response of a given networked microphone device to a particular wake word causes the given networked microphone device to listen, via a microphone, for a voice command following the particular wake word, wherein the one or more networked microphones devices are a subset of networked microphone devices in a household, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises;

determining that the one or more networked microphone devices are in audible vicinity of the audio content and

in response to determining that the one or more networked microphones are in audible vicinity of the audio content, sending, via the network interface to the one or more networked microphone devices, instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device; and

playing back the audio content via one or more speakers.

10. The tangible, non-transitory, computer-readable media of claim 9, wherein the playback device comprises the given networked microphone device, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

while playing back the audio content, recording, via the microphone, the audio content being played back; and

disabling respective wake responses of the given networked microphone device to the one or more wake words within the recorded audio content.

11. The tangible, non-transitory, computer-readable media of claim 9, wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

before playing back the audio content, modifying the audio content to incorporate acoustic markers in segments of the audio content that represent respective wake words, wherein detecting the acoustic markers causes the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

12. The tangible, non-transitory, computer-readable media of claim 9, wherein detecting the one or more wake words comprises applying multiple wake-word detection algorithms to the audio content, wherein the multiple wake-word detection algorithms comprise a first wake-word detection algorithm for a first voice service and a second wake-word detection algorithm for a second voice service, and wherein applying multiple wake-word detection algorithms to the audio content before the audio content is played back by the playback device comprises:

applying, to the audio content before the audio content is played back by the playback device, the first wake-word detection algorithm for the first voice service to detect at least one first wake word for the first voice service; and

applying, to the audio content before the audio content is played back by the playback device, the second wake-word detection algorithm for the second voice service to detect at least one second wake word for the second voice service, wherein the second wake word is a different word than the first wake word.

13. The tangible, non-transitory computer-readable medium of claim 9, wherein the one or more networked microphone devices comprise respective playback devices, and wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in a synchronous playback configuration with the playback device.

14. The tangible, non-transitory computer-readable medium of claim 9, wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in audible vicinity of the playback device.

15. A method comprising

receiving, via a network interface of a playback device, data representing audio content for playback by the playback device;

before the audio content is played back by the playback device, detecting, by the playback device in the audio content, one or more wake words for one or more voice services;

causing, by the playback device, one or more networked microphone devices to disable its respective wake response to the detected one or more wake words during playback of the audio content by the playback device, wherein, when enabled, the wake response of a given networked microphone device to a particular wake word causes the given networked microphone device to listen, via a microphone, for a voice command following the particular wake word, wherein the one or more networked microphones devices are a subset of networked microphone devices in a household, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises;

determining that the one or more networked microphone devices are in audible vicinity of the audio content and

in response to determining that the one or more networked microphones are in audible vicinity of the audio content, sending, via the network interface to the one or more networked microphone devices, instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device; and

playing back, by the playback device, the audio content via one or more speakers.

16. The method of claim 15, wherein the playback device comprises the given networked microphone device, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

while playing back the audio content, recording, via the microphone, the audio content being played back; and

disabling respective wake responses of the given networked microphone device to the one or more wake words within the recorded audio content.

17. The method of claim 15, wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises:

before playing back the audio content, modifying the audio content to incorporate acoustic markers in segments of the audio content that represent respective wake words, wherein detecting the acoustic markers causes the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

18. The method of claim 15, wherein detecting the one or more wake words comprises applying multiple wake-word detection algorithms to the audio content, wherein the multiple wake-word detection algorithms comprise a first wake-word detection algorithm for a first voice service and a second wake-word detection algorithm for a second voice service, and wherein applying multiple wake-word detection algorithms to the audio content before the audio content is played back by the playback device comprises:

applying, to the audio content before the audio content is played back by the playback device, the first wake-word detection algorithm for the first voice service to detect at least one first wake word for the first voice service; and

applying, to the audio content before the audio content is played back by the playback device, the second wake-word detection algorithm for the second voice service to detect at least one second wake word for the second voice service, wherein the second wake word is a different word than the first wake word.

19. The method of claim 15, wherein the one or more networked microphone devices comprise respective playback devices, and wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in a synchronous playback configuration with the playback device.

20. The method of claim 15, wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in audible vicinity of the playback device.