Reducing speech session resource use in a speech assistant
View Patent ↗A method of utilizing a speech assistant, the speech assistant designed to provide a voice input and speech output capability, the method comprising, enabling the use of the speech assistant for communication with a user, and terminating the speech assistant when the communication is complete. The method further comprises receiving a notification from a native application associated with the communication, and activating a sub-portion of the speech assistant, to enable outputting of the notification using speech output, thereby enabling the use of speech output for periodic announcements without enabling the speech assistant.
1. A method comprising:
activating a speech assistant for performing an interactive speech process with a user, the speech assistant comprising a speech input function and a speech output function; and
performing, using the speech assistant, the interactive speech process, which comprises:
conducting an initial communication with the user;
conditioned upon a determination that the initial communication is complete, deactivating the speech input function and the speech output function;
while the speech input function and the speech output function are deactivated, queuing a plurality of process statuses generated for the interactive speech process;
while the speech input function and the speech output function are deactivated, determining which of the plurality of process statuses are to cause activation of the speech output function, resulting in first subset of the plurality of process statuses that is to cause activation of the speech output function, and a second subset of the plurality of process statuses that is not to cause activation of the speech output function;
activating the speech output function;
while the speech input function is deactivated, using the speech output function to output one or more speech notifications based on the first subset; and
after using the speech output function to output the one or more speech notifications, deactivating the speech output function a second time.
2. The method of claim 1 , wherein the speech output function comprises a text-to-speech output function.
3. The method of claim 1 , wherein performing the interactive speech process further comprises:
after deactivating the speech output function the second time, queuing an additional plurality of process statuses generated for the interactive speech process;
while the speech input function and the speech output function are deactivated, determining that none of the additional plurality of process statuses are to cause activation of the speech output function; and
after determining that none of the additional plurality of process statuses are to cause activation of the speech output function, determining that the interactive speech process is complete.
4. The method of claim 3 , wherein the additional plurality of process statuses is not used as a basis for outputting speech to the user.
5. The method of claim 3 , wherein performing the interactive speech process further comprises:
after the initial communication is complete and conditioned upon a determination that additional notifications are needed to complete the interactive speech process, setting a flag in a native application that generates the plurality of process statuses and the additional plurality of process statuses; and
conditioned upon determining that the interactive speech process is complete, unsetting the flag in the native application.
6. The method of claim 5 , wherein performing the interactive speech process further comprises:
outputting, via the native application, text associated with the one or more speech notifications.
7. The method of claim 1 , wherein performing the interactive speech process further comprising:
conditioned upon determining that the interactive speech process is complete, terminating the speech assistant.
8. An apparatus comprising:
one or more processors; and
memory storing executable instructions that, when executed by the one or more processors, cause the apparatus to:
activate a speech assistant for performing an interactive speech process with a user, the speech assistant comprising a speech input function and a speech output function; and
perform, using the speech assistant, the interactive speech process, which comprises:
conducting an initial communication with the user;
conditioned upon a determination that the initial communication is complete, deactivating the speech input function and the speech output function;
while the speech input function and the speech output function are deactivated, queuing a plurality of process statuses generated for the interactive speech process;
while the speech input function and the speech output function are deactivated, determining which of the plurality of process statuses are to cause activation of the speech output function, resulting in a first subset of the plurality of process statuses that is to cause activation of the speech output function, and a second subset of the plurality of process statuses that is not to cause activation of the speech output function;
activating the speech output function;
while the speech input function is deactivated, using the speech output function to output one or more speech notifications based on the first subset; and
after using the speech output function to output the one or more speech notifications, deactivating the speech output function a second time.
9. The apparatus of claim 8 , wherein the speech output function comprises a text-to-speech output function.
10. The apparatus of claim 8 , wherein the interactive speech process further comprises:
after deactivating the speech output function the second time, queuing an additional plurality of process statuses generated for the interactive speech process;
while the speech input function and the speech output function are deactivated, determining that none of the additional plurality of process statuses are to cause activation of the speech output function; and
after determining that none of the additional plurality of process statuses are to cause activation of the speech output function, determining that the interactive speech process is complete.
11. The apparatus of claim 10 , wherein the additional plurality of process statuses is not used as a basis for outputting speech to the user.
12. The apparatus of claim 10 , wherein the interactive speech process further comprises:
after the initial communication is complete and conditioned upon a determination that additional notifications are needed to complete the interactive speech process, setting a flag in a native application that generates the plurality of process statuses and the additional plurality of process statuses; and
conditioned upon determining that the interactive speech process is complete, unsetting the flag in the native application.
13. The apparatus of claim 12 , wherein the interactive speech process further comprises:
outputting, via the native application, text associated with the one or more speech notifications.
14. The apparatus of claim 8 , wherein the interactive speech process further comprises:
conditioned upon determining that the interactive speech process is complete, terminating the speech assistant.
15. A method comprising:
activating a speech assistant for performing an interactive speech process with a user, the speech assistant comprising a speech input function and a speech output function; and
performing, using the speech assistant, the interactive speech process, which comprises:
conducting an initial communication with the user;
conditioned upon a determination that the initial communication is complete, deactivating the speech input function and the speech output function;
while the speech input function and the speech output function are deactivated, queuing a plurality of process statuses generated for the interactive speech process;
while the speech input function and the speech output function are deactivated and conditioned upon expiration of a timer, determining that at least one process status has been queued;
while the speech input function and the speech output function are deactivated, determining which of the plurality of process statuses are to cause activation of the speech output function, resulting in a subset of the plurality of process statuses that are to cause activation of the speech output function;
activating the speech output function;
while the speech input function is deactivated, using the speech output function to output one or more speech notifications based on the subset;
after using the speech output function to output the one or more speech notifications, deactivating the speech output function a second time; and
conditioned upon a determination that additional notifications are needed to complete the interactive speech process, selecting between (a) proceeding to determine that at least one process status has been queued conditioned upon expiration of the timer a second time and (b) proceeding to terminate the speech assistant.
16. The method of claim 15 , wherein the speech output function comprises a text-to-speech output function.
17. The method of claim 15 , wherein the interactive speech process further comprises:
after deactivating the speech output function the second time, queuing an additional plurality of process statuses generated for the interactive speech process; and
while the speech input function and the speech output function are deactivated, determining that none of the additional plurality of process statuses are to cause activation of the speech output function.
18. The method of claim 17 , wherein the additional plurality of process statuses is not used as a basis for outputting speech to the user.
19. The method of claim 17 , wherein the interactive speech process further comprises:
after the initial communication is complete, setting a flag in a native application that generates the plurality of process statuses and the additional plurality of process statuses; and
conditioned upon determining that the interactive speech process is complete, unsetting the flag in the native application.
20. The method of claim 19 , wherein performing the interactive speech process further comprises:
outputting, via the native application, text associated with the one or more speech notifications.