System and method of providing conversational visual prosody for talking heads
View Patent ↗A system and method of controlling the movement of a virtual agent while the agent is listening to a human user during a conversation is disclosed. The method comprises receiving speech data from the user, performing a prosodic analysis of the speech data and controlling the virtual agent movement according to the prosodic analysis.
1. A method of providing movements by a virtual agent during a conversation with a user, the method utilizing a database associated sets of culturally based movements of the virtual agent, the method comprising:
determining a culture associated with the user;
receiving speech from the user;
selecting from the database a set of listening movements for the virtual agent reactive to the received speech and appropriate to the determined culture of the user; and
controlling movements of the virtual agent when the virtual agent listens to the user according to the selected set of listening movements and a prosodic analysis of the received speech.
2. The method of claim 1 , wherein controlling the movements of the virtual agent further comprises controlling the movement of the virtual agent while the virtual agent is transitioning between listening to speaking using transitional movements.
3. A computing device for providing movements by a virtual agent during a conversation with a user, the method utilizing a associated with sets of movements of the virtual agent, the computing device comprising:
a module configured to determine a culture associated with the user;
a module configured to receive user speech;
a module configured to select from the database a set of listening movements for the virtual agent reactive to the received speech and appropriate to the determined culture of the user; and
a module configured to control movements of the virtual agent when the virtual agent listens to the user according to the selected set of listening movements and a prosodic analysis the received speech.
4. The computing device of claim 3 , wherein the module configured to control movements of the virtual agent further controls the movement of the virtual agent while the virtual agent is transitioning between listening to speaking using transitional movements.
5. A computer-readable medium storing instructions for controlling a computing device to provide user-specific animated entity movements by a virtual agent during a conversation with a user, the method utilizing a database associated with sets of movements of the virtual agent, the instructions comprising:
determining a culture associated with the user;
receiving speech from the user;
selecting from the database a set of listening movements for the virtual agent reactive to the received speech and appropriate to the determined culture of the user; and
controlling movements of the virtual agent when the virtual agent listens to the user according to the selected set of listening movements and a prosodic analysis of the received speech.