Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_94b6928c88206bf76b96ce7d001bb137 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L2021-105 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L2015-025 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L21-12 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L13-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L15-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L15-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T13-40 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T13-80 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L15-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T13-205 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L21-10 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G10L21-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T13-40 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G10L15-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G10L15-08 |
filingDate |
2020-01-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d1c20a2f87f2280923a55aacf1685c9f http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a324d751fe9f70753045dfa889ecf6be http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_46706f2c4952ea5033eba7d0d7d451d5 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4d1d0ef15d9c5ddf8f7a5a80f9d26de5 |
publicationDate |
2021-07-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
AU-2020211809-A1 |
titleOfInvention |
Real-time generation of speech animation |
abstract |
To realistically animate a String (such as a sentence) a hierarchical search algorithm is provided to search for stored examples (Animation Snippets) of sub-strings of the String, in decreasing order of sub-string length, and concatenate retrieved sub-strings to complete the String of speech animation. In one embodiment, real-time generation of speech animation uses model visemes to predict the animation sequences at onsets of visemes and a look-up table based (data-driven) algorithm to predict the dynamics at transitions of visemes. Specifically posed Model Visemes may be blended with speech animation generated using another method at corresponding time points in the animation when the visemes are to be expressed. An Output Weighting Function is used to map Speech input and Expression input into Muscle-Based Descriptor weightings. |
priorityDate |
2019-01-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |