Playback device supporting concurrent voice assistants
Disclosed herein are example techniques to support multiple voice assistant services. An example implementation may involve a playback device capturing audio from the one or more microphones into one or more buffers as a sound data stream monitoring the sound data stream for a wake word associated with a specific voice assistant service and monitoring the sound data stream for a wake word associated with the media playback system. The playback device generates a second wake-word event corresponding to a voice input when sound data matching the wake word associated with the media playback system in a portion of the sound data stream is detected. The playback device determines that the voice input includes sound data matching one or more playback commands and sends sound data representing the voice input to a voice assistant associated with the media playback system for processing of the second voice input.
1. A playback device of a media playback system, the playback device comprising:
one or more microphones;
a network interface;
one or more processors; and
data storage having stored therein instructions executable by the one or more processors to cause the playback device to perform functions comprising:
capturing audio from the one or more microphones into one or more buffers as a sound data stream;
monitoring, via a first wake word engine, the sound data stream from the one or more microphones for a wake word associated with a specific voice assistant service;
monitoring, via a second wake word engine, the sound data stream from the one or more microphones for a wake word associated with the media playback system;
generating a first wake-word event corresponding to a first voice input when the first wake-word engine detects sound data matching the wake word associated with the specific voice assistant service in a first portion of the sound data stream;
based on generating the first wake-word event, sending sound data representing the first voice input to the specific voice assistant for processing of the first voice input;
generating a second wake-word event corresponding to a second voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a second portion of the sound data stream;
determining that the second voice input includes sound data matching one or more playback commands; and
based on (i) generating the second wake-word event and (ii) determining that the second voice input includes sound data matching one or more playback commands, sending sound data representing the second voice input to a voice assistant associated with the media playback system for processing of the second voice input.
2. The playback device of claim 1 , wherein sending the sound data representing the second voice input to the voice assistant associated with the media playback system comprises streaming, via the network interface, the sound data representing the second voice input to one or more remote servers associated with the media playback system.
3. The playback device of claim 1 , wherein the functions further comprise:
receiving, from the voice assistant associated with the media playback system, at least one playback instruction corresponding to the one or more playback commands; and
performing the at least one playback instruction.
4. The playback device of claim 3 , wherein the voice assistant associated with the media playback system identifies specific media content based on the second voice input, and wherein the at least one playback instruction instructs the playback device to play back the specific media content.
5. The playback device of claim 1 , wherein the functions further comprise:
generating a third wake-word event corresponding to a third voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a third portion of the sound data stream;
determining that the third voice input includes sound data matching a particular playback command; and
based on (i) generating the third wake-word event and (ii) determining that the third voice input includes sound data matching the particular playback command, performing the particular playback command.
6. The playback device of claim 1 , wherein the functions further comprise:
generating a third wake-word event corresponding to a third voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a third portion of the sound data stream;
determining that the third voice input includes sound data matching one or more smart home commands; and
based on (i) generating the third wake-word event and (ii) determining that the third voice input includes sound data matching one or more smart home commands, causing one or more smart home devices to carry out at least one smart home instruction corresponding to the one or more smart home commands.
7. The playback device of claim 6 , wherein causing the one or more smart home devices to carry out at least one smart home instruction corresponding to the one or more smart home commands comprises:
sending sound data representing the third voice input to a voice assistant for processing of the third voice input.
8. A method to be performed by a playback device of a media playback system, the method comprising:
capturing audio from one or more microphones into one or more buffers as a sound data stream;
monitoring, via a first wake word engine, the sound data stream from the one or more microphones for a wake word associated with a specific voice assistant service;
monitoring, via a second wake word engine, the sound data stream from the one or more microphones for a wake word associated with the media playback system;
generating a first wake-word event corresponding to a first voice input when the first wake-word engine detects sound data matching the wake word associated with the specific voice assistant service in a first portion of the sound data stream;
based on generating the first wake-word event, sending sound data representing the first voice input to the specific voice assistant for processing of the first voice input;
generating a second wake-word event corresponding to a second voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a second portion of the sound data stream;
determining that the second voice input includes sound data matching one or more playback commands; and
based on (i) generating the second wake-word event and (ii) determining that the second voice input includes sound data matching one or more playback commands, sending sound data representing the second voice input to a voice assistant associated with the media playback system for processing of the second voice input.
9. The method of claim 8 , wherein sending the sound data representing the second voice input to the voice assistant associated with the media playback system comprises streaming, via a network interface, the sound data representing the second voice input to one or more remote servers associated with the media playback system.
10. The method of claim 8 , further comprising:
receiving, from the voice assistant associated with the media playback system, at least one playback instruction corresponding to the one or more playback commands; and
performing the at least one playback instruction.
11. The method of claim 10 , wherein the voice assistant associated with the media playback system identifies specific media content based on the second voice input, and wherein the at least one playback instruction instructs the playback device to play back the specific media content.
12. The method of claim 8 , further comprising:
generating a third wake-word event corresponding to a third voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a third portion of the sound data stream;
determining that the third voice input includes sound data matching a particular playback command; and
based on (i) generating the third wake-word event and (ii) determining that the third voice input includes sound data matching the particular playback command, performing the particular playback command.
13. The method of claim 8 , further comprising:
generating a third wake-word event corresponding to a third voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a third portion of the sound data stream;
determining that the third voice input includes sound data matching one or more smart home commands; and
based on (i) generating the third wake-word event and (ii) determining that the third voice input includes sound data matching one or more smart home commands, causing one or more smart home devices to carry out at least one smart home instruction corresponding to the one or more smart home commands.
14. The method of claim 13 , wherein causing the one or more smart home devices to carry out at least one smart home instruction corresponding to the one or more smart home commands comprises:
sending sound data representing the third voice input to a voice assistant for processing of the third voice input.
15. A non-transitory computer-readable medium having instructions stored thereon that are executable by one or more processors to cause a playback device to perform functions comprising:
capturing audio from one or more microphones into one or more buffers as a sound data stream;
monitoring, via a first wake word engine, the sound data stream from the one or more microphones for a wake word associated with a specific voice assistant service;
monitoring, via a second wake word engine, the sound data stream from the one or more microphones for a wake word associated with a media playback system, wherein the media playback system comprises the playback device;
generating a first wake-word event corresponding to a first voice input when the first wake-word engine detects sound data matching the wake word associated with the specific voice assistant service in a first portion of the sound data stream;
based on generating the first wake-word event, sending sound data representing the first voice input to the specific voice assistant for processing of the first voice input;
generating a second wake-word event corresponding to a second voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a second portion of the sound data stream;
determining that the second voice input includes sound data matching one or more playback commands; and
based on (i) generating the second wake-word event and (ii) determining that the second voice input includes sound data matching one or more playback commands, sending sound data representing the second voice input to a voice assistant associated with the media playback system for processing of the second voice input.
16. The non-transitory computer-readable medium of claim 15 , wherein sending the sound data representing the second voice input to the voice assistant associated with the media playback system comprises streaming, via a network interface, the sound data representing the second voice input to one or more remote servers associated with the media playback system.
17. The non-transitory computer-readable medium of claim 15 , wherein the functions further comprise:
receiving, from the voice assistant associated with the media playback system, at least one playback instruction corresponding to the one or more playback commands; and
performing the at least one playback instruction.
18. The non-transitory computer-readable medium of claim 17 , wherein the voice assistant associated with the media playback system identifies specific media content based on the second voice input, and wherein the at least one playback instruction instructs the playback device to play back the specific media content.
19. The non-transitory computer-readable medium of claim 15 , wherein the functions further comprise:
generating a third wake-word event corresponding to a third voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a third portion of the sound data stream;
determining that the third voice input includes sound data matching a particular playback command; and
based on (i) generating the third wake-word event and (ii) determining that the third voice input includes sound data matching the particular playback command, performing the particular playback command.
20. The non-transitory computer-readable medium of claim 15 , wherein the functions further comprise:
generating a third wake-word event corresponding to a third voice input when the second wake-word engine detects sound data matching the wake word associated with the media playback system in a third portion of the sound data stream;
determining that the third voice input includes sound data matching one or more smart home commands; and
based on (i) generating the third wake-word event and (ii) determining that the third voice input includes sound data matching one or more smart home commands, causing one or more smart home devices to carry out at least one smart home instruction corresponding to the one or more smart home commands.
21. The non-transitory computer-readable medium of claim 20 , wherein causing the one or more smart home devices to carry out at least one smart home instruction corresponding to the one or more smart home commands comprises:
sending sound data representing the third voice input to a voice assistant for processing of the third voice input.