Natural human-computer interaction for virtual personal assistant systems
Technologies for natural language interactions with virtual personal assistant systems include a computing device configured to capture audio input, distort the audio input to produce a number of distorted audio variations, and perform speech recognition on the audio input and the distorted audio variants. The computing device selects a result from a large number of potential speech recognition results based on contextual information. The computing device may measure a user's engagement level by using an eye tracking sensor to determine whether the user is visually focused on an avatar rendered by the virtual personal assistant. The avatar may be rendered in a disengaged state, a ready state, or an engaged state based on the user engagement level. The avatar may be rendered as semitransparent in the disengaged state, and the transparency may be reduced in the ready state or the engaged state. Other embodiments are described and claimed.
1. An apparatus comprising:
at least one memory;
instructions; and
processor circuitry to execute the instructions to:
cause a display screen to present an avatar in a first state, the avatar having eyes, the eyes of the avatar in a first position directed away from a user in the first state;
cause the display screen to present the avatar in a second state, the second state different than the first state, the eyes of the avatar in a second position directed toward the user in the second state to indicate that the avatar is available to interact with the user; and
in response to an input from the user, cause the display screen to present the avatar in a third state to provide a response to the user, the third state different than the first state and the second state.
2. The apparatus of claim 1 , wherein the input includes a speech input.
3. The apparatus of claim 1 , wherein the processor circuitry is to cause the display screen to present the avatar as making eye contact with the user when the eyes are in the second position.
4. The apparatus of claim 1 , wherein the input is a first input and the processor circuitry is to cause the display screen to present the avatar in the second state from the first state in response to a second input.
5. The apparatus of claim 4 , wherein the second input includes a trigger word.
6. The apparatus of claim 1 , wherein the first state corresponds to an idle state.
7. At least one volatile or non-volatile memory comprising instructions that, when executed, cause at least one processor to at least:
cause a display screen to present an avatar in a first state, the avatar having eyes, an eye gaze of the avatar in a first direction in the first state;
detect a presence of a user based on a first user input;
cause the display screen to present the avatar in a second state from the first state in response to the detection of the presence of the user, the second state different than the first state, the second state corresponding to a ready state of the avatar to interact with the user, the eye gaze of the avatar in a second direction in the second state;
detect a second user input; and
cause the display screen to present the avatar in a third state to provide a response to the second user input, the third state different than the first state and the second state.
8. The at least one volatile or non-volatile memory of claim 7 , wherein the first user input is a speech input.
9. The at least one volatile or non-volatile memory of claim 8 , wherein the instructions, when executed, cause the at least one processor to detect a trigger word in the speech input.
10. The at least one volatile or non-volatile memory of claim 7 , wherein the instructions, when executed, cause the at least one processor to cause the display screen to present the avatar as making eye contact with the user when the eye gaze is in the second direction.
11. The at least volatile or non-volatile memory of claim 10 , wherein the instructions, when executed, cause the at least one processor to cause the display screen to present the avatar with the eye gaze in the first direction from the eye gaze in the second direction when the avatar is in the third state.
12. The at least one volatile or non-volatile memory of claim 7 , wherein the instructions, when executed, cause the at least one processor to cause the display screen to present at least a portion of a body of the avatar as opaque.
13. The at least one volatile or non-volatile memory of claim 7 , wherein the first state is an idle state.
14. A system comprising:
a display screen;
at least one memory;
instructions; and
processor circuitry to execute the instructions to:
cause the display screen to present a virtual personal assistant avatar in a first state, the virtual personal assistant avatar exhibiting a human face including eyes;
cause the display screen to present the virtual personal assistant avatar in a second state, the second state different than the first state, the second state indicating that the virtual personal assistant avatar is available to interact with a user;
cause the display screen to display the eyes of the virtual personal assistant avatar in a first position at a first time;
cause the display screen to display the eyes of the virtual personal assistant avatar in a second position at a second time;
detect a user input; and
cause the display screen to display the virtual personal assistant avatar in a third state to provide a response to the user input, the third state different than the first state and the second state.
15. The system of claim 14 , wherein the processor circuitry is to cause the virtual personal assistant avatar to face out of the display screen.
16. The system of claim 14 , wherein the processor circuitry is to detect a presence of the user.
17. The system of claim 16 , wherein the processor circuitry is to detect the presence of the user based on image data.
18. The system of claim 16 , wherein the processor circuitry is to cause the display screen to display the virtual personal assistant avatar in the second state from the first state in response to the detection of the presence of the user.
19. The system of claim 14 , wherein the first state is an idle state.
20. The system of claim 14 , wherein the eyes of the virtual personal assistant avatar are directed away from the user in the first position and toward the user in the second position.