Multiple voice services
Disclosed herein are example techniques to identify a voice service to process a voice input. An example implementation may involve an NMD receiving, via a microphone, voice data indicating a voice input. The NMD may identify, from among multiple voice services registered to a media playback system, a voice service to process the voice input and cause, via a network interface, the identified voice service to process the voice input.
1. A networked microphone device 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 networked microphone device to perform a method comprising:
continuously recording, via the microphone array, audio into a buffer;
analyzing the recorded audio using multiple wake-word detection algorithms running concurrently on the one or more processors, each wake-word detection algorithm corresponding to a respective voice assistant service;
when a particular wake-word detection algorithm of the multiple wake-word detection algorithms detects, in the recorded audio, a wake-word corresponding to a particular voice assistant service, querying, via the network interface, the particular voice assistant service with a voice command following the detected wake-word within the recorded audio, wherein the voice command comprises a search query;
receiving, from one or more servers of the particular voice assistant service via the network interface in response to the query, data representing search results, the search results including audio tracks corresponding to the search query, wherein the search results are unique to the particular voice assistant service among the multiple voice assistant services; and
playing back at least one audio track from the search results via the one or more amplifiers configured to drive the one or more speakers.
2. The networked microphone device of claim 1 , wherein the search query indicates an artist name, and wherein the search results include identifiers indicating respective locations at a streaming audio service of audio tracks by an artist corresponding to the artist name, and wherein playing back at least one audio track from the search results comprises streaming the at least one audio track from the respective locations at the streaming audio service of the audio tracks.
3. The networked microphone device of claim 1 , wherein the search query indicates an album name, and wherein the search results include identifiers indicating respective locations at a streaming audio service of audio tracks on an album corresponding to the album name, and wherein playing back at least one audio track from the search results comprises streaming the at least one audio track from the respective locations at the streaming audio service of the audio tracks.
4. The networked microphone device of claim 1 , wherein the search query indicates an artist name, and wherein the search results include an identifier indicating a location at a streaming audio service of an Internet radio station corresponding to the artist name, and wherein playing back at least one audio track from the search results comprises streaming the Internet radio station from the location at the streaming audio service.
5. The networked microphone device of claim 1 , wherein the search query indicates an artist name, and wherein the search results include biographical information about an artist corresponding to the artist name, and wherein the method further comprises playing back the biographical information.
6. The networked microphone device of claim 1 , wherein the method further comprises:
when the particular wake-word detection algorithm of the multiple wake-word detection algorithms detects, in the recorded audio, the wake-word corresponding to the particular voice assistant service, querying, via the network interface, an additional voice assistant service with the voice command following the detected wake-word within the recorded audio;
receiving, from one or more servers of the additional voice assistant service via the network interface in response to the query, data representing additional search results; and
outputting, via the one or more speakers, an indication that search results from the additional voice assistant service are available.
7. The networked microphone device of claim 6 , wherein the search query indicates an artist name, and wherein the additional search results include biographical information about an artist corresponding to the artist name.
8. The networked microphone device of claim 6 , wherein the search results include identifiers indicating respective locations of audio tracks at a first streaming audio service, and wherein the additional search results include identifiers indicating respective locations of audio tracks at a second streaming audio service.
9. A tangible, non-transitory computer-readable medium having stored therein instructions executable by one or more processors to cause a networked microphone device to perform a method comprising:
continuously recording, via a microphone array of the networked microphone device, audio into a buffer;
analyzing the recorded audio using multiple wake-word detection algorithms running concurrently on one or more processors of the networked microphone device, each wake-word detection algorithm corresponding to a respective voice assistant service;
when a particular wake-word detection algorithm of the multiple wake-word detection algorithms detects, in the recorded audio, a wake-word corresponding to a particular voice assistant service, querying, via a network interface of the networked microphone device, the particular voice assistant service with a voice command following the detected wake-word within the recorded audio, wherein the voice command comprises a search query;
receiving, from one or more servers of the particular voice assistant service via the network interface in response to the query, data representing search results, the search results including audio tracks corresponding to the search query, wherein the search results are unique to the particular voice assistant service among the multiple voice assistant services; and
playing back at least one audio track from the search results via one or more amplifiers of the networked microphone device configured to drive one or more speakers.
10. The tangible, non-transitory computer-readable medium of claim 9 , wherein the search query indicates an artist name, and wherein the search results include identifiers indicating respective locations at a streaming audio service of audio tracks by an artist corresponding to the artist name, and wherein playing back at least one audio track from the search results comprises streaming the at least one audio track from the respective locations at the streaming audio service of the audio tracks.
11. The tangible, non-transitory computer-readable medium of claim 9 , wherein the search query indicates an album name, and wherein the search results include identifiers indicating respective locations at a streaming audio service of audio tracks on an album corresponding to the album name, and wherein playing back at least one audio track from the search results comprises streaming the at least one audio track from the respective locations at the streaming audio service of the audio tracks.
12. The tangible, non-transitory computer-readable medium of claim 9 , wherein the search query indicates an artist name, and wherein the search results include an identifier indicating a location at a streaming audio service of an Internet radio station corresponding to the artist name, and wherein playing back at least one audio track from the search results comprises streaming the Internet radio station from the location at the streaming audio service.
13. The tangible, non-transitory computer-readable medium of claim 9 , wherein the search query indicates an artist name, and wherein the search results include biographical information about an artist corresponding to the artist name, and wherein the method further comprises playing back the biographical information.
14. The tangible, non-transitory computer-readable medium of claim 9 , wherein the method further comprises:
when the particular wake-word detection algorithm of the multiple wake-word detection algorithms detects, in the recorded audio, the wake-word corresponding to the particular voice assistant service, querying, via the network interface, an additional voice assistant service with the voice command following the detected wake-word within the recorded audio;
receiving, from one or more servers of the additional voice assistant service via the network interface in response to the query, data representing additional search results; and
outputting, via the one or more speakers, an indication that search results from the additional voice assistant service are available.
15. The tangible, non-transitory computer-readable medium of claim 14 , wherein the search query indicates an artist name, and wherein the additional search results include biographical information about an artist corresponding to the artist name.
16. The tangible, non-transitory computer-readable medium of claim 14 , wherein the search results include identifiers indicating respective locations of audio tracks at a first streaming audio service, and wherein the additional search results include identifiers indicating respective locations of audio tracks at a second streaming audio service.
17. A method comprising:
continuously recording, via a microphone array of a networked microphone device, audio into a buffer;
analyzing, via the networked microphone device, the recorded audio using multiple wake-word detection algorithms running concurrently on one or more processors of the networked microphone device, each wake-word detection algorithm corresponding to a respective voice assistant service;
when a particular wake-word detection algorithm of the multiple wake-word detection algorithms detects, in the recorded audio, a wake-word corresponding to a particular voice assistant service, querying, via a network interface of the networked microphone device, the particular voice assistant service with a voice command following the detected wake-word within the recorded audio, wherein the voice command comprises a search query;
receiving, from one or more servers of the particular voice assistant service via the network interface in response to the query, data representing search results, the search results including audio tracks corresponding to the search query, wherein the search results are unique to the particular voice assistant service among the multiple voice assistant services; and
playing back at least one audio track from the search results via one or more amplifiers of the networked microphone device configured to drive one or more speakers.
18. The method of claim 17 , wherein the search query indicates an artist name, and wherein the search results include identifiers indicating respective locations at a streaming audio service of audio tracks by an artist corresponding to the artist name, and wherein playing back at least one audio track from the search results comprises streaming the at least one audio track from the respective locations at the streaming audio service of the audio tracks.
19. The method of claim 17 , wherein the search query indicates an album name, and wherein the search results include identifiers indicating respective locations at a streaming audio service of audio tracks on an album corresponding to the album name, and wherein playing back at least one audio track from the search results comprises streaming the at least one audio track from the respective locations at the streaming audio service of the audio tracks.
20. The method of claim 17 , wherein the search query indicates an artist name, and wherein the search results include an identifier indicating a location at a streaming audio service of an Internet radio station corresponding to the artist name, and wherein playing back at least one audio track from the search results comprises streaming the Internet radio station from the location at the streaming audio service.
21. The method of claim 17 , wherein the search query indicates an artist name, and wherein the search results include biographical information about an artist corresponding to the artist name, and wherein the method further comprises playing back the biographical information.
22. The method of claim 17 , wherein the method further comprises:
when the particular wake-word detection algorithm of the multiple wake-word detection algorithms detects, in the recorded audio, the wake-word corresponding to the particular voice assistant service, querying, via the network interface, an additional voice assistant service with the voice command following the detected wake-word within the recorded audio;
receiving, from one or more servers of the additional voice assistant service via the network interface in response to the query, data representing additional search results; and
outputting, via the one or more speakers, an indication that search results from the additional voice assistant service are available.
23. The method of claim 22 , wherein the search query indicates an artist name, and wherein the additional search results include biographical information about an artist corresponding to the artist name.
24. The method of claim 22 , wherein the search results include identifiers indicating respective locations of audio tracks at a first streaming audio service, and wherein the additional search results include identifiers indicating respective locations of audio tracks at a second streaming audio service.