Voice enablement and disablement of speech processing functionality
Methods and devices for enabling and disabling applications using voice are described herein. In some embodiments, an individual speak an utterance to their electronic device, which may send audio data representing the utterance to a backend system. The backend system may generate text data representing the utterance, and may determine that an intent of the utterance was for an application to be enabled or disabled for their user account on the backend system. If, for instance, the intent was to enable the application, the backend system may receive one or more rules for performing functionalities of the application, as well as one or more sample templates of sample utterances and sample responses that future utterances may use when requesting the application. Furthermore, one or more invocation phrases that may be used within the future utterances to invoke the application may be received, along with slot values for the sample templates.
1. A computer-implemented method, comprising:
receiving first input data;
processing, using a speech processing component, the first input data to determine that the first input data corresponds to a first command to enable future invocation of a first application, wherein, prior to receipt of the first input data, a voice interface of the first application was not enabled such that a response from the first application was unable to be invoked in response to a spoken user input;
based at least in part on determining that the first input data corresponds to the first command, configuring an updated speech processing component to cause a first action of the first application to be performed in response to recognition of a first phrase, wherein configuring the updated speech processing component comprises enabling the voice interface for the first application;
after configuring the updated speech processing component, receiving first audio data;
processing the first audio data using the updated speech processing component to detect the first phrase; and
based at least in part on detection of the first phrase, causing the first action to be performed by the first application.
2. The computer-implemented method of claim 1 , further comprising:
prior to receiving the first input data, receiving a request to operate the voice interface of the first application; and
after receiving the request to operate the voice interface of the first application, presenting a prompt to enable the future invocation of the first application,
wherein the first input data is received after presenting the prompt.
3. The computer-implemented method of claim 2 , wherein causing the first action to be performed comprises invoking a first response from the first application.
4. The computer-implemented method of claim 1 , wherein the first input data corresponds to a touch input.
5. The computer-implemented method of claim 1 , wherein the first input data is received by a first device associated with a first user account and the method further comprises:
associating the updated speech processing component with the first user account.
6. The computer-implemented method of claim 1 , further comprising, after configuring the updated speech processing component:
receiving second input data;
determining that the second input data corresponds to a second command to disable the future invocation of the first application; and
based at least in part on the second input data corresponding to the second command, configuring a further updated speech processing component.
7. The computer-implemented method of claim 1 , further comprising:
receiving the first input data from a first device;
determining that a first speech processing component is associated with the first device;
configuring the updated speech processing component at least in part by updating the first speech processing component;
receiving the first audio data from the first device; and
determining that the updated speech processing component is associated with the first device.
8. The computer-implemented method of claim 1 , further comprising:
determining at least one word associated with the first input data,
wherein configuring the updated speech processing component causes the at least one word to be associated with the first action.
9. 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 first input data;
processing, using a speech processing component, the first input data to determine that the first input data corresponds to a first command to enable future invocation of a first application, wherein, prior to receipt of the first input data, a voice interface of the first application was not enabled such that a response from the first application was unable to be invoked in response to a spoken user input;
based at least in part on determining that the first input data corresponds to the first command, configure an updated speech processing component to cause a first action of the first application to be performed in response to recognition of a first phrase, wherein configuring the updated speech processing component comprises enabling the voice interface for the first application;
after configuration of the updated speech processing component, receive first audio data;
process the first audio data using the updated speech processing component to detect the first phrase; and
based at least in part on detection of the first phrase, cause the first action to be performed by the first application.
10. The system of claim 9 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
prior to receiving the first input data, receive a request to operate the voice interface of the first application; and
after receiving the request to operate the voice interface of the first application, present a prompt to enable the future invocation of the first application,
wherein the first input data is received after presentation of the prompt.
11. The system of claim 10 , wherein the instructions that cause the first action to be performed comprise instructions that, when executed by the at least one processor, cause the system to invoke a first response from the first application.
12. The system of claim 10 , wherein the first input data corresponds to a touch input.
13. The system of claim 9 , wherein the first input data is received by a first device associated with a first user account and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
associate the updated speech processing component with the first user account.
14. The system of claim 9 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to, after configuration of the updated speech processing component:
receive second input data;
determine that the second input data corresponds to a second command to disable the future invocation of the first application; and
based at least in part on the second input data corresponding to the second command, configure a further updated speech processing component.
15. The system of claim 9 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive the first input data from a first device;
determine that a first speech processing component is associated with the first device;
configure the updated speech processing component at least in part by updating the first speech processing component;
receive the first audio data from the first device; and
determine that the updated speech processing component is associated with the first device.
16. The system of claim 9 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine at least one word associated with the first input data,
wherein the instructions that cause the system to configure the updated speech processing component cause the at least one word to be associated with the first action.