Dialog system with automatic reactivation of speech acquiring mode
Embodiments of the disclosure generally relate to a dialog system allowing for automatically reactivating a speech acquiring mode after the dialog system delivers a response to a user request. The reactivation parameters, such as a delay, depend on a number of predetermined factors and conversation scenarios. The embodiments further provide for a method of operating of the dialog system. An exemplary method comprises the steps of: activating a speech acquiring mode, receiving a first input of a user, deactivating the speech acquiring mode, obtaining a first response associated with the first input, delivering the first response to the user, determining that a conversation mode is activated, and, based on the determination, automatically re-activating the speech acquiring mode within a first predetermined time period after delivery of the first response to the user.
1. A method implemented by one or more processors and comprising:
activating a speech acquiring mode of the dialog system in response to a user speaking an activation phrase;
receiving, via the speech acquiring mode after activating the speech acquiring mode, a first spoken input of a user;
deactivating, after receiving the first spoken input of the user, the speech acquiring mode;
processing the first spoken input, using an automatic speech recognizer, to generate a recognized input;
processing the recognized input, using a natural language processing module, to determine a meaning representation for the recognized input;
obtaining, based on the meaning representation, a response associated with the first spoken input;
delivering the response in response to receiving the first spoken input;
selecting, from a plurality of candidate time periods, a particular time period for the speech acquiring mode to last when the speech acquiring mode is automatically reactivated responsive to the first spoken input;
determining, in response to a conversation mode being activated, to automatically re-activate the speech acquiring mode responsive to the first spoken input; and
automatically re-activating the speech acquiring mode responsive to the first spoken input and in response to determining to automatically re-activate the speech acquiring mode,
wherein automatically re-activating the speech acquiring mode comprises causing the speech acquiring mode to last for the selected particular time period.
2. The method of claim 1 , wherein selecting the particular time period is based on a length of the response.
3. The method of claim 1 , wherein selecting the particular time period is based on a type of the response.
4. The method of claim 1 , wherein selecting the particular time period is based on one or more properties of the first spoken input.
5. The method of claim 4 , wherein obtaining the response based on the meaning representation comprises:
retrieving text based on the meaning representation;
transforming the text into a machine-generated audio signal; and
using the machine-generated audio signal as the response.
6. The method of claim 5 , wherein automatically re-activating the speech acquiring mode occurs immediately after the machine-generated audio signal has been provided as output to the user.
7. A user device, the user device comprising:
instructions stored in memory,
one or more processors executing the stored instructions to cause the one or more processors to:
activate a speech acquiring mode in response to a user speaking an activation phrase;
receive, via the speech acquiring mode after activating the speech acquiring mode, a first spoken input of a user;
deactivate, after receiving the first spoken input of the user, the speech acquiring mode;
obtain, in response to the first spoken input:
a response that includes content to be rendered responsive to the first spoken input, and
metadata associated with the response, wherein the metadata dictates whether the speech acquiring mode is to be automatically reactivated after rendering of the content of the response;
render the content in response to receiving the response;
determine, based on the metadata, whether to automatically reactivate the speech acquiring mode after rendering of the content of the response;
in response to determining, based on the metadata, that the speech acquiring mode is to be automatically reactivated after rendering of the content of the response:
automatically re-activate the speech acquiring mode after rendering of the content of the response; and
in response to determining, based on the metadata, that the speech acquiring mode is not to be automatically reactivated after rendering of the content of the response:
bypass automatically re-activating the speech acquiring mode after rendering of the content of the response.
8. The user device of claim 7 ,
wherein the metadata dictates that the speech acquiring mode is to be automatically reactivated and further dictates a time period for the speech acquiring mode to last when the speech acquiring mode is automatically reactivated after rendering of the content of the response; and
wherein in automatically re-activating the speech acquiring mode after rendering of the content of the response, one or more of the processors are to re-activate the speech acquiring mode for the time period in response to the metadata dictating the time period for the speech acquiring mode to last when the speech acquiring mode is automatically reactivated after rendering of the content of the response.
9. The user device of claim 7 , wherein the user device further comprises a speaker and wherein the content is an audio message and is rendered via the speaker.
10. The user device of claim 7 , wherein in obtaining the response one or more of the processors are to obtain the response via a communication network and from a dialog system.
11. The user device of claim 7 , wherein the metadata, that dictates whether the speech acquiring mode is to be automatically reactivated after rendering of the content of the response, comprises a flag with either a true value or a false value.
12. The user device of claim 7 , wherein the user device further comprises a speaker, wherein the content is an audio message and is rendered via the speaker, wherein the metadata further dictates one or more parameters of the audio message, and wherein in rendering the audio message one or more of the processors are to render the audio message with the one or more parameters.
13. The user device of claim 12 , wherein the one or more parameters include a volume of the response.
14. The user device of claim 7 , wherein the response includes the metadata.