Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310249214> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4310249214 abstract "Visual speech is hard to recreate by human hands because animation itself is a time-consuming task: both precision and detail must be considered and match the expectations of the developers, but above all, those of the audience. To solve this problem, some approaches has been designed to help accelerate the animation of characters faces, as procedural animation or speech-lip synchronization, where the most common areas for researching these methods are Computer Vision and Machine Learning. However, in general, these tools can have any of these main problems: difficulty on adapting to another language, subject or animation software, high hardware specifications, or the results can be receipted as robotic. Our work presents a Deep Learning model for automatic expressive facial animation using audio. We extract generic audio features from expressive audio speeches rich in phonemes for nonidiom focus speech processing and emotion recognition. From videos used for training, we extracted the landmarks for frame-speech targeting and have the model learn animation for phonemes pronunciation. We evaluated four variants of our model (two function losses and with emotion conditioning) by using a user perspective survey where the one using a Reconstruction Loss Function with emotion training conditioning got more natural results and score in synchronization with the approval of the majority of interviewees. For perception of naturalness, it obtained a 38.89% of the total votes of approval and for language synchronization obtained the highest average score with 65.55% (98.33 of a 150 total points) for English, German and Korean languages." @default.
- W4310249214 created "2022-11-30" @default.
- W4310249214 creator A5026792531 @default.
- W4310249214 creator A5035162654 @default.
- W4310249214 creator A5076194651 @default.
- W4310249214 date "2022-11-26" @default.
- W4310249214 modified "2023-10-16" @default.
- W4310249214 title "Emotional 3D speech visualization from 2D audio visual data" @default.
- W4310249214 doi "https://doi.org/10.1142/s1793962324500028" @default.
- W4310249214 hasPublicationYear "2022" @default.
- W4310249214 type Work @default.
- W4310249214 citedByCount "0" @default.
- W4310249214 crossrefType "journal-article" @default.
- W4310249214 hasAuthorship W4310249214A5026792531 @default.
- W4310249214 hasAuthorship W4310249214A5035162654 @default.
- W4310249214 hasAuthorship W4310249214A5076194651 @default.
- W4310249214 hasConcept C107457646 @default.
- W4310249214 hasConcept C121332964 @default.
- W4310249214 hasConcept C121684516 @default.
- W4310249214 hasConcept C127162648 @default.
- W4310249214 hasConcept C134537474 @default.
- W4310249214 hasConcept C138591656 @default.
- W4310249214 hasConcept C138885662 @default.
- W4310249214 hasConcept C154945302 @default.
- W4310249214 hasConcept C162324750 @default.
- W4310249214 hasConcept C169760540 @default.
- W4310249214 hasConcept C187736073 @default.
- W4310249214 hasConcept C204321447 @default.
- W4310249214 hasConcept C26760741 @default.
- W4310249214 hasConcept C2778562939 @default.
- W4310249214 hasConcept C2780451532 @default.
- W4310249214 hasConcept C2780844864 @default.
- W4310249214 hasConcept C28490314 @default.
- W4310249214 hasConcept C31258907 @default.
- W4310249214 hasConcept C36464697 @default.
- W4310249214 hasConcept C41008148 @default.
- W4310249214 hasConcept C41895202 @default.
- W4310249214 hasConcept C502989409 @default.
- W4310249214 hasConcept C62520636 @default.
- W4310249214 hasConcept C69369342 @default.
- W4310249214 hasConcept C86803240 @default.
- W4310249214 hasConceptScore W4310249214C107457646 @default.
- W4310249214 hasConceptScore W4310249214C121332964 @default.
- W4310249214 hasConceptScore W4310249214C121684516 @default.
- W4310249214 hasConceptScore W4310249214C127162648 @default.
- W4310249214 hasConceptScore W4310249214C134537474 @default.
- W4310249214 hasConceptScore W4310249214C138591656 @default.
- W4310249214 hasConceptScore W4310249214C138885662 @default.
- W4310249214 hasConceptScore W4310249214C154945302 @default.
- W4310249214 hasConceptScore W4310249214C162324750 @default.
- W4310249214 hasConceptScore W4310249214C169760540 @default.
- W4310249214 hasConceptScore W4310249214C187736073 @default.
- W4310249214 hasConceptScore W4310249214C204321447 @default.
- W4310249214 hasConceptScore W4310249214C26760741 @default.
- W4310249214 hasConceptScore W4310249214C2778562939 @default.
- W4310249214 hasConceptScore W4310249214C2780451532 @default.
- W4310249214 hasConceptScore W4310249214C2780844864 @default.
- W4310249214 hasConceptScore W4310249214C28490314 @default.
- W4310249214 hasConceptScore W4310249214C31258907 @default.
- W4310249214 hasConceptScore W4310249214C36464697 @default.
- W4310249214 hasConceptScore W4310249214C41008148 @default.
- W4310249214 hasConceptScore W4310249214C41895202 @default.
- W4310249214 hasConceptScore W4310249214C502989409 @default.
- W4310249214 hasConceptScore W4310249214C62520636 @default.
- W4310249214 hasConceptScore W4310249214C69369342 @default.
- W4310249214 hasConceptScore W4310249214C86803240 @default.
- W4310249214 hasLocation W43102492141 @default.
- W4310249214 hasOpenAccess W4310249214 @default.
- W4310249214 hasPrimaryLocation W43102492141 @default.
- W4310249214 hasRelatedWork W1578215370 @default.
- W4310249214 hasRelatedWork W2004789217 @default.
- W4310249214 hasRelatedWork W2050837419 @default.
- W4310249214 hasRelatedWork W2120181525 @default.
- W4310249214 hasRelatedWork W2350725650 @default.
- W4310249214 hasRelatedWork W2374762698 @default.
- W4310249214 hasRelatedWork W2610177858 @default.
- W4310249214 hasRelatedWork W2887659124 @default.
- W4310249214 hasRelatedWork W3004910051 @default.
- W4310249214 hasRelatedWork W4283028469 @default.
- W4310249214 isParatext "false" @default.
- W4310249214 isRetracted "false" @default.
- W4310249214 workType "article" @default.