CPC G06T 13/80 (2013.01) [G10L 21/055 (2013.01)] | 20 Claims |
1. A method comprising:
identifying, using one or more processors, a plurality of animation elements within a computer animation model;
processing audio inputs received at a microphone of a user device to identify a set of audio characteristics;
generating a set of normalized audio energy values based on the set of audio characteristics;
selecting a minimum audio energy threshold and a maximum audio energy threshold;
identifying a plurality of motion patterns and a plurality speed harmonics associated with the plurality of animation elements;
determining a plurality of motion data values comprising a state-space description of the plurality of motion patterns and the plurality of speed harmonics for the plurality of animation elements within the computer model;
calculating a model motion energy for each value of the set of motion data values;
assigning a probability value to each of the plurality of motion data values for the state-space description, a subset of the plurality of motion values being assigned a probability of zero based on the respective model motion energies being less than the minimum audio energy threshold or greater than the maximum audio energy threshold; and
in response to assigning the probability value to each of the plurality of motion data values, pseudo-randomly animating the computer animation model based on the motion data values for the state-space description whose assigned probability value is greater than zero.
|