Audio-driven facial animation with adaptive speech rate

A processor comprising:

• one or more circuits to perform operations comprising:
• determining that a rate of speech associated with an audio segment exceeds a threshold;
• based at least on the rate of speech exceeding the threshold, upsampling a first set of features associated with the audio segment into a second set of features that is different in size than the first set of features;
• and
• generating, using one or more machine learning models and based at least on at least a subset of the second set of features, a facial animation output corresponding to the audio segment.

A system comprising:

• one or more processing units to perform operations comprising:
• determining that a rate of speech associated with an audio segment exceeds a threshold;
• based at least on the rate of speech exceeding the threshold, upsampling a first set of features associated with the audio segment into a second set of features that is different in size than the first set of features;
• and
• generating, using one or more machine learning models and based at least on at least a subset of the second set of features, a facial animation output corresponding to the audio segment.