Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360888921> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4360888921 abstract "Synthesizing realistic co-speech gestures is an important and yet unsolved problem for creating believable motions that can drive a humanoid robot to interact and communicate with human users. Such capability will improve the impressions of the robots by human users and will find applications in education, training, and medical services. One challenge in learning the co-speech gesture model is that there may be multiple viable gesture motions for the same speech utterance. The deterministic regression methods can not resolve the conflicting samples and may produce over-smoothed or damped motions. We proposed a two-stage model to address this uncertainty issue in gesture synthesis by modeling the gesture segments as discrete latent codes. Our method utilizes RQ-VAE in the first stage to learn a discrete codebook consisting of gesture tokens from training data. In the second stage, a two-level autoregressive transformer model is used to learn the prior distribution of residual codes conditioned on input speech context. Since the inference is formulated as token sampling, multiple gesture sequences could be generated given the same speech input using top-k sampling. The quantitative results and the user study showed the proposed method outperforms the previous methods and is able to generate realistic and diverse gesture motions." @default.
- W4360888921 created "2023-03-25" @default.
- W4360888921 creator A5045112037 @default.
- W4360888921 creator A5058214616 @default.
- W4360888921 creator A5066604966 @default.
- W4360888921 date "2023-03-03" @default.
- W4360888921 modified "2023-09-26" @default.
- W4360888921 title "Co-Speech Gesture Synthesis using Discrete Gesture Token Learning" @default.
- W4360888921 doi "https://doi.org/10.48550/arxiv.2303.12822" @default.
- W4360888921 hasPublicationYear "2023" @default.
- W4360888921 type Work @default.
- W4360888921 citedByCount "0" @default.
- W4360888921 crossrefType "posted-content" @default.
- W4360888921 hasAuthorship W4360888921A5045112037 @default.
- W4360888921 hasAuthorship W4360888921A5058214616 @default.
- W4360888921 hasAuthorship W4360888921A5066604966 @default.
- W4360888921 hasBestOaLocation W43608889211 @default.
- W4360888921 hasConcept C119599485 @default.
- W4360888921 hasConcept C127413603 @default.
- W4360888921 hasConcept C127759330 @default.
- W4360888921 hasConcept C149782125 @default.
- W4360888921 hasConcept C151730666 @default.
- W4360888921 hasConcept C154945302 @default.
- W4360888921 hasConcept C159437735 @default.
- W4360888921 hasConcept C159877910 @default.
- W4360888921 hasConcept C165801399 @default.
- W4360888921 hasConcept C207347870 @default.
- W4360888921 hasConcept C2775852435 @default.
- W4360888921 hasConcept C2776214188 @default.
- W4360888921 hasConcept C2779343474 @default.
- W4360888921 hasConcept C28490314 @default.
- W4360888921 hasConcept C33923547 @default.
- W4360888921 hasConcept C38652104 @default.
- W4360888921 hasConcept C41008148 @default.
- W4360888921 hasConcept C48145219 @default.
- W4360888921 hasConcept C66322947 @default.
- W4360888921 hasConcept C86803240 @default.
- W4360888921 hasConcept C90509273 @default.
- W4360888921 hasConceptScore W4360888921C119599485 @default.
- W4360888921 hasConceptScore W4360888921C127413603 @default.
- W4360888921 hasConceptScore W4360888921C127759330 @default.
- W4360888921 hasConceptScore W4360888921C149782125 @default.
- W4360888921 hasConceptScore W4360888921C151730666 @default.
- W4360888921 hasConceptScore W4360888921C154945302 @default.
- W4360888921 hasConceptScore W4360888921C159437735 @default.
- W4360888921 hasConceptScore W4360888921C159877910 @default.
- W4360888921 hasConceptScore W4360888921C165801399 @default.
- W4360888921 hasConceptScore W4360888921C207347870 @default.
- W4360888921 hasConceptScore W4360888921C2775852435 @default.
- W4360888921 hasConceptScore W4360888921C2776214188 @default.
- W4360888921 hasConceptScore W4360888921C2779343474 @default.
- W4360888921 hasConceptScore W4360888921C28490314 @default.
- W4360888921 hasConceptScore W4360888921C33923547 @default.
- W4360888921 hasConceptScore W4360888921C38652104 @default.
- W4360888921 hasConceptScore W4360888921C41008148 @default.
- W4360888921 hasConceptScore W4360888921C48145219 @default.
- W4360888921 hasConceptScore W4360888921C66322947 @default.
- W4360888921 hasConceptScore W4360888921C86803240 @default.
- W4360888921 hasConceptScore W4360888921C90509273 @default.
- W4360888921 hasLocation W43608889211 @default.
- W4360888921 hasOpenAccess W4360888921 @default.
- W4360888921 hasPrimaryLocation W43608889211 @default.
- W4360888921 hasRelatedWork W1974238679 @default.
- W4360888921 hasRelatedWork W1974379374 @default.
- W4360888921 hasRelatedWork W2602341155 @default.
- W4360888921 hasRelatedWork W2989134874 @default.
- W4360888921 hasRelatedWork W3016124757 @default.
- W4360888921 hasRelatedWork W3184187848 @default.
- W4360888921 hasRelatedWork W3197304116 @default.
- W4360888921 hasRelatedWork W3209239055 @default.
- W4360888921 hasRelatedWork W4308238098 @default.
- W4360888921 hasRelatedWork W4309584605 @default.
- W4360888921 isParatext "false" @default.
- W4360888921 isRetracted "false" @default.
- W4360888921 workType "article" @default.