Method and voice assistance apparatus for providing an intelligence response
Provided are a method and an apparatus for providing an intelligent voice response at a voice assistant device. The method includes obtaining, by a voice assistant device, a voice input from a user, identifying non-speech input while obtaining the voice input, determining a correlation between the voice input and the non-speech input, and generating, based on the correlation, a response comprising an action related to the correlation or a suggestion related to the correlation.
1. A method for providing an intelligent response, the method comprising:
obtaining, by a voice assistant device, a voice input comprising a speech signal including a partial voice command of a user;
extracting a non-speech signal from the obtained voice input;
determining a correlation between the speech signal and the non-speech signal;
determining an intent corresponding to the partial voice command based on the correlation; and
generating, based on the correlation and the determined intent, a response to the partial voice command.
2. The method of claim 1 , further comprising:
mapping the non-speech signal into at least one event occurring in an ambience of the user.
3. The method of claim 2 , wherein the at least one event comprises at least one of an event indicating a presence of a human other than the user, a domestic sound event, an outdoor sound event, or an event indicating a mood.
4. The method of claim 2 , further comprising identifying the at least one event based on a profile of the user.
5. The method of claim 2 , wherein the determining the correlation comprises:
extracting one or more context parameters from the voice input, wherein the one or more context parameters is used to identify a natural language processing (NLP) domain capable of handling the voice input; and
mapping the at least one event to the NLP domain using a predefined correlation matrix.
6. The method of claim 5 , wherein the predefined correlation matrix represents correlations between a plurality of predefined events related to a plurality of non-speech inputs and NLP domains related to the voice assistant device.
7. The method of claim 5 , wherein the predefined correlation matrix is generated based on at least one of a profile of the user, a location of the voice assistant device, and a type of devices connected to the voice assistant device.
8. The method of claim 1 , wherein the response comprises a natural language response.
9. The method of claim 1 , wherein the response comprises a suggestion of launching at least one application installed in a device of the user.
10. The method of claim 9 , wherein the at least one application comprises a booking application related to the correlation.
11. The method of claim 9 , wherein the suggestion is generated based on data included in the at least one application or generated in the at least one application.
12. The method of claim 1 , wherein suggestion comprises an advertisement content related to the non-speech signal.
13. The method of claim 12 , wherein the advertisement content is generated based on a profile of the user and metadata received from a database.
14. An apparatus of providing an intelligent response, the apparatus comprising:
a receiver which obtains a voice input comprising a speech signal including a partial voice command of a user;
a processor configured to extract a non-speech signal from the obtained voice input, determine a correlation between the speech signal and the non-speech signal, determine an intent corresponding to the partial voice command based on the correlation, and generate a response to the partial voice command based on the correlation and the determined intent.
15. The apparatus of claim 14 , wherein the processor is configured to map the non-speech signal into at least one event occurring in an ambience of the user.
16. The apparatus of claim 15 , wherein the processor is configured to determine the correlation based on extracting one or more context parameters from the voice input, wherein the one or more context parameters is used to identify a natural language processing (NLP) domain capable of handling the voice input and mapping the at least one event to the NLP domain using a predefined correlation matrix.
17. The apparatus of claim 16 , wherein the predefined correlation matrix represents correlations between a plurality of predefined events related to a plurality of non-speech inputs and NLP domains related to the apparatus.
18. The apparatus of claim 16 , wherein the predefined correlation matrix is generated based on at least one a profile of the user, a location of the apparatus, and a type of devices connected to the apparatus.
19. A non-transitory computer readable storage medium having a computer readable instructions stored therein, when executed by at least one processor, the at least one processor controls to perform a method for providing an intelligent response, the method comprising:
obtaining a voice input comprising a speech signal including a partial voice command of a user;
extracting a non-speech signal from the obtained voice input;
determining a correlation between the speech signal and the non-speech signal;
determining an intent corresponding to the partial voice command based on the correlation; and
generating, based on the correlation and the determined intent, a response to the partial voice command.