Voice controlled system
A distributed voice controlled system has a primary assistant and at least one secondary assistant. The primary assistant has a housing to hold one or more microphones, one or more speakers, and various computing components. The secondary assistant is similar in structure, but is void of speakers. The voice controlled assistants perform transactions and other functions primarily based on verbal interactions with a user. The assistants within the system are coordinated and synchronized to perform acoustic echo cancellation, selection of a best audio input from among the assistants, and distributed processing.
1. A computer-implemented method comprising:
receiving, at a first device, speech input;
generating first audio data representing the speech input;
receiving, at the first device, second audio data representing the speech input; and
selecting the second audio data for speech processing.
2. The computer-implemented method as recited in claim 1 , further comprising causing the first device to perform speech processing on the second audio data.
3. The computer-implemented method as recited in claim 2 , further comprising identifying a word or phrase from the speech input based at least in part on the speech processing of the second audio data.
4. The computer-implemented method as recited in claim 3 , further comprising outputting, in response to the word or phrase and using an audio speaker of the first device, an audio file.
5. The computer-implemented method as recited in claim 1 , wherein the second audio data is generated at a second device in wireless communication with the first device.
6. The computer-implemented method as recited in claim 1 , further comprising:
determining a first confidence value associated with detection of a wake word in the first audio data;
determining a second confidence value associated with detection of the wake word in the second audio data; and
selecting the second audio data for speech processing is based at least in part on the second confidence value being higher than the first confidence value.
7. The computer-implemented method as recited in claim 1 , further comprising performing, at the first device, the speech processing on the second audio data.
8. The computer-implemented method as recited in claim 1 , further comprising:
determining a proximity of a user to the first device or a second device in wireless communication with the first device;
sending, from the first device to the second device and based at least in part on the proximity, the second audio data; and
generating, at the second device, an audio output representing the second audio data.
9. A device comprising:
a microphone;
a wireless interface; and
one or more processors configured to execute instructions stored in non-transitory computer-readable media to cause the device to:
receive, using the microphone, a speech input;
generate first audio data representing the speech input;
receive, using the wireless interface, second audio data representing the speech input; and
select either the first audio data or the second audio data for speech processing.
10. The device as recited in claim 9 , wherein selecting either the first audio data or the second audio data for speech processing comprises selecting the second audio data, and the one or more processors are further configured to execute instructions stored in non-transitory computer-readable media to cause the device to perform speech processing on the second audio data based at least partly on selecting the second audio data.
11. The device as recited in claim 9 , wherein the one or more processors are further configured to execute instructions stored in non-transitory computer-readable media to cause the device to identify a word or phrase from the speech input based at least in part on the speech processing of the second audio data.
12. The device as recited in claim 9 , wherein the one or more processors are further configured to execute instructions stored in non-transitory computer-readable media to cause the device to send, using the wireless interface, the second audio data to a secondary device for outputting at the secondary device.
13. The device as recited in claim 9 , wherein the one or more processors are further configured to execute instructions stored in non-transitory computer-readable media to further cause the device to determine a confidence value associated with detection of a wake word in the second audio data, and wherein selecting either the first audio data or the second audio data for speech processing comprises selecting the second audio data based at least in part on the confidence value.
14. The device as recited in claim 9 , wherein the second audio data is generated, at a secondary device in wireless communication with the first device, to represent the speech input.
15. The device as recited in claim 9 , wherein the second audio data comprises a composite of the first audio data and the speech input.
16. The device as recited in claim 9 , wherein the second audio data is received from a remote server in communication with the device.
17. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to:
receive, using a microphone of a first device, speech input;
generate first audio data representing the speech input;
receive, from a second device in wireless communication with the first device, second audio data generated at the second device representing the speech input; and
selecting the first audio data for speech processing.
18. The system as recited in claim 17 , wherein the instructions, when executed by the one or more processors, further cause the system to perform, at the first device, speech processing on the first audio data or the second audio data.
19. The system as recited in claim 18 , wherein the instructions, when executed by the one or more processors, further cause the system to identify a word or phrase from the speech input based at least in part on the speech processing of the first audio data or the second audio data.
20. The system as recited in claim 19 , wherein the instructions, when executed by the one or more processor, further cause the system to determine a confidence value associated with detection of a wake word in the second audio data, wherein selecting the second audio data for speech processing is based at least in part on the confidence value.