Voice user interface with personality
The present invention provides a voice user interface with personality. In one embodiment, a method includes executing a voice user interface, and controlling the voice user interface to provide the voice user interface with a personality. The method includes selecting a prompt based on various context situations, such as a previously selected prompt and the user's experience with using the voice user interface.
1. A method comprising:
initiating, at one or more computing devices, a finite state machine;
receiving, at the one or more computing devices, a voice input;
interpreting, at the one or more computing devices, the received voice input, comprising:
transitioning to a domain state functionality of the finite state machine,
selecting a generic prompt corresponding to the domain state functionality, and
selecting a specific prompt corresponding to the generic prompt, wherein the specific prompt comprises a variant of the generic prompt and also corresponds to the domain state functionality; and
transmitting, at the one or more computing devices, the specific prompt in a response.
2. The method of claim 1 , wherein the voice input comprises a phonetic, short phrase input.
3. The method of claim 1 , wherein the domain state functionality comprises one or more of the set of voice mail, email, faxes, pages, personal information manager (PIM), calendar, and browser.
4. The method of claim 2 , further comprising:
recognizing the phonetic, short phrase input using a grammar definition language (GDL) that performs a function of speech recognition grammar.
5. The method of claim 2 , further comprising:
recognizing a specific name for the phonetic, short phrase; and
recognizing a generic name for the phonetic, short phrase, corresponding to the specific name, using a grammar definition language (GDL) that performs a function of speech recognition grammar.
6. The method of claim 2 , further comprising:
matching the phonetic, short phrase input to a phonetic, short phrase response corresponding to a recognition grammar.
7. The method of claim 6 , further comprising:
matching the phonetic, short phrase input using ‘more like/less like’ logic.
8. The method of claim 6 , further comprising:
matching the phonetic, short phrase input by dynamically updating a grammar library.
9. The method of claim 6 , further comprising:
parsing messages, constructing prompts, constructing grammar, and erasing previous grammar.
10. The method of claim 9 , further comprising:
matching the phonetic, short phrase input using user recognition logic.
11. The method of claim 6 , wherein the recognition grammar corresponds to a voice interface personality.
12. The method of claim 1 , wherein the generic prompt is defined for a plurality of prompt suites.
13. The method of claim 12 , wherein the specific prompt is defined for a corresponding particular prompt suite of the plurality of prompt suites.
14. The method of claim 1 , wherein the specific prompt is selected based on a configuration parameter.
15. The method of claim 14 , wherein the configuration parameter comprises a level of expertise.
16. An article of manufacture including a non-transitory computer-readable storage medium having stored hereon computer-executable instructions, execution of which, by a computing device, causes the computing device to perform operations for performing speech recognition, the operations comprising:
initiating a finite state machine;
receiving a voice input;
interpreting the received voice input, comprising:
transitioning to a domain state functionality of the finite state machine,
selecting a generic prompt corresponding to the domain state functionality, and
selecting a specific prompt corresponding to the generic prompt, wherein the specific prompt comprises a variant of the generic prompt and also corresponds to the domain state functionality; and
transmitting the specific prompt in a response.
17. A system of speech recognition, comprising an executable finite state machine programmed to:
initiate a finite state machine;
receive a voice input;
interpret the received voice input, comprising:
transitioning to a domain state functionality of the finite state machine,
selecting a generic prompt corresponding to the domain state functionality, and
selecting a specific prompt corresponding to the generic prompt, wherein the specific prompt comprises a variant of the generic prompt and also corresponds to the domain state functionality; and
transmit the specific prompt in a response.
18. A system comprising:
means for initiating a finite state machine;
means for receiving a voice input;
means for interpreting the received voice input, comprising:
means for transitioning to a domain state functionality of the finite state machine,
means for selecting a generic prompt corresponding to the domain state functionality, and
means for selecting a specific prompt corresponding to the generic prompt, wherein the specific prompt comprises a variant of the generic prompt and also corresponds to the domain state functionality; and
means for transmitting the specific prompt in a response.