Speech-processing system
A system may include first and second speech-processing systems. The first speech-processing system may process received audio data and determine that a command represented therein is associated with a second speech-processing system. The first speech-processing system may send command data to the second speech-processing system and receive response data in return. The first speech-processing system may then process the response data to determine second response data that includes an indication of the second speech-processing system and cause output of audio corresponding to the second response data.
1 . A computer-implemented method, comprising:
receiving input data corresponding to a natural-language command;
determining the input data includes a first representation indicating that the natural-language command is intended to be processed by a first natural-language processing system associated with a user profile;
performing, based at least in part on the first representation, first natural-language processing of the input data by a first natural-language processing component of a first natural-language processing system to generate first data;
determining, that a second natural-language processing system is associated with the user profile, the second natural-language processing system corresponding to a second representation different from the first representation, indicating that the second natural-language processing system is intended to perform processing;
determining, based at least in part on the first data, that a second natural-language processing component of the second natural-language processing system is configured to determine output data responsive to the natural-language command;
sending the first data to the second natural-language processing component for second natural-language processing by the second natural-language processing system;
receiving, from the second natural-language processing component, second data corresponding to a first response to the natural-language command determined by the second natural-language processing performed by the second natural-language processing system, the second data including an indication of the second natural-language processing component;
determining, by the first natural-language processing system and based at least in part on the second data, third data corresponding to a second response to the natural-language command, the second response corresponding to a natural-language response; and
causing output corresponding to the third data by the first natural-language processing component.
2 . The computer-implemented method of claim 1 , further comprising:
including, in the second response, the indication of the second natural-language processing component.
3 . The computer-implemented method of claim 1 , further comprising:
determining the third data corresponding to the second response based at least in part on a grammar style associated with the first natural-language processing component.
4 . The computer-implemented method of claim 1 , wherein the third data does not include the indication of the second natural-language processing component.
5 . The computer-implemented method of claim 1 , wherein the first data is sent via an application programming interface (API) call.
6 . The computer-implemented method of claim 5 , wherein the API call corresponds to the second natural-language processing component.
7 . The computer-implemented method of claim 5 , wherein the second data corresponds to results of the API call.
8 . The computer-implemented method of claim 1 , further comprising:
configuring the first data to include a natural-language representation of at least a portion of the natural-language command.
9 . The computer-implemented method of claim 1 , wherein the second data comprises command data corresponding to a device and wherein the method further comprises:
sending the command data to the device.
10 . The computer-implemented method of claim 1 , further comprising:
receiving fourth data corresponding to permission for the first natural-language processing component to invoke the second natural-language processing component.
11 . A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive input data corresponding to a natural-language command;
determine the input data includes a first representation indicating that the natural-language command is intended to be processed by a first natural-language processing system associated with a user profile;
perform, based at least in part on the first representation, first natural-language processing of the input data by a first natural-language processing component of a first natural-language processing system to generate first data;
determine, that a second natural-language processing system is associated with the user profile, the second natural-language processing system corresponding to a second representation different from the first representation, indicating that the second natural-language processing system is intended to perform processing;
determine, based at least in part on the first data, that a second natural-language processing component of the second natural-language processing system is configured to determine output data responsive to the natural-language command;
send the first data to the second natural-language processing component for second natural-language processing by the second natural-language processing system;
receive, from the second natural-language processing component, second data corresponding to a first response to the natural-language command determined by the second natural-language processing performed by the second natural-language processing component, the second data including an indication of the second natural-language processing component;
determine, by the first natural-language processing system and based at least in part on the second data, third data corresponding to a second response to the natural-language command, the second response corresponding to a natural-language response; and
cause output corresponding to the third data by the first natural-language processing component.
12 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
include, in the second response, the indication of the second natural-language processing component.
13 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine the third data corresponding to the second response based at least in part on a grammar style associated with the first natural-language processing component.
14 . The system of claim 11 , wherein the third data does not include the indication of the second natural-language processing component.
15 . The system of claim 11 , wherein the first data is sent via an application programming interface (API) call.
16 . The system of claim 15 , wherein the API call corresponds to the second natural-language processing component.
17 . The system of claim 15 , wherein the second data corresponds to results of the API call.
18 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
configure the first data to include a natural-language representation of at least a portion of the natural-language command.
19 . The system of claim 11 , wherein the second data comprises command data corresponding to a device and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
send the command data to the device.
20 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive fourth data corresponding to permission for the first natural-language processing component to invoke the second natural-language processing component.