Multi-modal interaction with intelligent assistants in voice command devices
A method comprising detecting an activation of an intelligent assistant on an electronic device, waking up the intelligent assistant from a sleep mode in response to the activation, and determining an amount of vocabulary the intelligent assistant acts upon during a listening mode based on a type of the activation.
1. An electronic device, comprising:
a display;
a microphone;
a speaker;
a sensor; and
at least one processor coupled to the display, the microphone, the speaker, and the sensor, and configured to:
based on an occurrence of a first event that activates a speech recognition function of the electronic device, provide a first feedback via at least one of the display or the speaker, the first event comprising identifying a wake word based on a first speech signal obtained via the microphone;
based on a voice command not being identified in a second speech signal obtained via the microphone, after providing the first feedback, provide a speech response via the speaker;
based on an occurrence of a second event that activates the speech recognition function of the electronic device, provide a second feedback via at least one of the display or the speaker, the second event comprising detecting an external object within a proximity of the electronic device based on a second signal obtained via the sensor, and the second feedback being different from the first feedback; and
based on a voice command not being identified in a third speech signal obtained via the microphone, after providing the second feedback, provide a visual response via the display.
2. The electronic device of claim 1 , wherein the first feedback comprises a feedback based on a sound and the second feedback comprises a feedback based on a visual indication.
3. The electronic device of claim 1 , wherein the first feedback comprises a feedback based on a sound, provided via the speaker, and a feedback based on a visual indication, provided via the display.
4. The electronic device of claim 1 , wherein the at least one processor is further configured to, based on no speech signal obtained via the microphone after providing the speech response, provide another speech response different from the speech response.
5. The electronic device of claim 4 , wherein the at least one processor is further configured to generate a timeout, based on no speech signal obtained within a predetermined time window via the microphone after providing the second speech signal, and
wherein the other speech response indicates the timeout due to an absence of a speech signal within the predetermined time window.
6. The electronic device of claim 5 , wherein the at least one processor is further configured to, based on generation of the timeout, provide a visual feedback indicating that the speech recognition function of the electronic device transitions to a sleep mode.
7. The electronic device of claim 1 , wherein the at least one processor is further configured to generate a timeout, based on no speech signal obtained via the microphone within a predetermined time window after providing the visual response.
8. The electronic device of claim 7 , wherein the at least one processor is further configured to, based on generation of the timeout, provide a visual feedback indicating that the speech recognition function of the electronic device transitions to a sleep mode.
9. The electronic device of claim 1 , wherein the at least one processor is further configured to generate a timeout based on no speech signal obtained within a first predetermined time window via the microphone after providing the first speech signal, and
the at least one processor is further configured to generate a timeout, based on no speech signal obtained via the microphone within a second predetermined time window after providing the visual response,
wherein the first predetermined time window is different from the second predetermined time window.
10. A method of operating an electronic device comprising a display, a microphone, a speaker, and a sensor, the method comprising:
based on an occurrence of a first event that activates a speech recognition function of the electronic device, providing a first feedback via at least one of the display or the speaker, the first event comprising identifying a wake word based on a first speech signal obtained via the microphone;
based on a voice command not being identified in a second speech signal obtained via the microphone after providing the first feedback, providing a speech response via the speaker;
based on an occurrence of a second event that activates the speech recognition function of the electronic device, providing a second feedback via at least one of the display or the speaker, the second event comprising detecting an external object based on a second signal obtained via the sensor, and the second feedback being different from the first feedback; and
based on a voice command not being identified in a third speech signal obtained via the microphone after providing the second feedback, providing a visual response via the display.
11. The method of claim 10 , wherein the first feedback comprises a feedback based on a sound and the second feedback comprises a feedback based on a visual indication.
12. The method of claim 10 , wherein the first feedback comprises a feedback based on a sound, provided via the speaker, and a feedback based on a visual indication, provided via the display.
13. The method of claim 10 , wherein the at least one processor is further configured to, based on no speech signal obtained via the microphone after providing the speech response, provide another speech response different from the speech response.
14. The method of claim 13 , wherein the at least one processor is further configured to generate a timeout, based on no speech signal obtained within a predetermined time window via the microphone after providing the second speech signal, and
wherein the other speech response indicates the timeout due to an absence of a speech signal within the predetermined time window.
15. The method of claim 14 , wherein the at least one processor is further configured to, based on generation of the timeout, provide a visual feedback indicating that the speech recognition function of the electronic device transitions to a sleep mode.
16. The method of claim 10 , wherein the at least one processor is further configured to generate a timeout, based on no speech signal obtained via the microphone within a predetermined time window after providing the visual response.
17. The method of claim 16 , wherein the at least one processor is further configured to, based on generation of the timeout, provide a visual feedback indicating that the speech recognition function of the electronic device transitions to a sleep mode.
18. The method of claim 10 , wherein the at least one processor is further configured to generate a timeout based on no speech signal obtained within a first predetermined time window via the microphone after providing the second speech signal, and
the at least one processor is further configured to generate a timeout, based on no speech signal obtained via the microphone within a second predetermined time window after providing the visual response,
wherein the first predetermined time window is different from the second predetermined time window.