US 10,360,716 B1Granted

Enhanced avatar animation

AssigneeAmazon Technologies, Inc.

InventorsPieter Sierd van der Meulen, Aditi Chandrashekhar Dixit, Sanjoy Ghosh

Life of this patent

Estimating the term…

Loading patent…

Abstract

Avatar animation may be enhanced to reflect emotion and other human traits when animated to read messages received from other users or other messages. A message may be analyzed to determine visual features associated with data in the message. The visual features may be depicted graphically by the avatar to create enhanced avatar animation. A text-based message may include indicators, such as punctuation, font, words, graphics, and/or other information, which may be extracted to create the visual features. This information may be used to select visual features as special animation, which may be implemented in animation of the avatar. Examples of visual features include animations of laugher, smiling, clapping, whistling, and/or other animations.

Claims20

Dependent claims

A method of generating animations for an avatar, the method comprising:

receiving a text message that includes text comprising an abbreviation and an emoticon;
determining, using an audio processor that performs text-to-speech conversions, phonemes based at least in part on the text included in the text message;
associating the emoticon with a first animation sequence performed by the avatar;
associating the abbreviation with a second animation sequence to be performed by the avatar;
determining, using a graphics processor, animation visemes to be performed by the avatar based at least in part on the phonemes, where a first animation viseme is associated with a first phoneme;
generating, at least partly using an audio mixer, speech data based at least in part on the phonemes;
generating visual synthesis markup language (VSML) text that identifies timing of the first animation sequence with respect to timing of speech generated from the speech data;
generating, at least partly using a graphics mixer, animation data based at least in part on the animation visemes, the first animation sequence, the second animation sequence, and the VSML text, the animation data to visually represent the speech data, the emoticon, and the abbreviation;
synchronizing at least a portion of the animation data with the speech data;
and
sending the animation data and the speech data to at least one user device.

8 more elements

A system comprising:

one or more processors;
and
memory to store computer-executable instructions that, when executed, cause the one or more processors to perform acts including:
receiving data to be output to a user device, the data including text having a text abbreviation and a non-speech visual action;
analyzing the data to determine an element of the data that is associated with the non-speech visual action represented by animation;
performing text-to-speech conversion of text in the data to create speech data;
determining a first animation sequence of the animation to represent the speech data;
associating a second animation sequence of the animation with the abbreviation, the second animation sequence depicting a second visual action performed by the avatar;
generating visual synthesis markup language (VSML) text that identifies timing of the first animation sequence with respect to timing of speech generated from the speech data;
synchronizing at least a portion of the first animation sequence and the second animation sequence with the speech data to at least coordinate playback of the segment of the speech data with the playback of the animation sequence;
and
sending the animation sequences and speech data to the user device.

9 more elements

Dependencies are inferred from the claim text.