Viseme data generation for presentation while content is output
AssigneeAmazon Technologies, Inc.
InventorsZoe Adams, Pete Klein, Derick Deller, Bradley Michael Richards, Anirudh Ranganath
Life of this patent
Estimating the term…
Abstract
Systems and methods for viseme data generation are disclosed. Uncompressed audio data is generated and/or utilized to determine the beats per minute of the audio data. Visemes are associated with the audio data utilizing a Viterbi algorithm and the beats per minute. A time-stamped list of viseme data is generated that associates the visemes with the portions of the audio data that they correspond to. An animatronic toy and/or an animation is caused to lip sync using the viseme data while audio corresponding to the audio data is output.
Claims20
A system comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving first data representing first content;
- analyzing the first data to determine, for words represented by a portion of the first content, lengths of time associated with individual ones of the words based at least in part on an overall length of time associated with the portion of the first content and a distribution of vowels associated with the words;
- determining viseme identifiers to associate with the portion of the first content based at least in part on the lengths of time associated with the individual ones of the words;
- generating viseme data that associates the viseme identifiers with the portion of the first content corresponding to the viseme identifiers;
- and
- causing a first device to:
- output the first content represented by the first data;
- and
- present a visual representation of the viseme data while the first content represented by the first data is output.
A method comprising:
- receiving first data representing first content;
- analyzing the first data to determine lengths of time associated with individual ones of words represented by a portion of the first content based at least in part on an overall length of time associated with the portion of the first content and a distribution of vowels associated with the words;
- determining viseme identifiers to associate with the portion of the first content based at least in part on the lengths of time associated with the individual ones of the words;
- generating viseme data that associates the viseme identifiers with the portion of the first content corresponding to the viseme identifiers;
- and
- causing a first device to:
- output the first content represented by the first data;
- and
- present a visual representation of the viseme data while the first content represented by the first data is output.
Dependencies are inferred from the claim text.