RESUMEN
Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture (DiTs-based). The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model's superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system's usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology. Supplementary videos and code can be accessed at https://zf223669.github.io/Diffmotion-v2-website/.
RESUMEN
Carbonylative homocoupling of arylzinc compounds 1 using 1 atm of CO and 1,2-dibromoethane as an oxidant was achieved in the presence of Rh-dppf catalyst, affording symmetrical diaryl ketones in good yields. Under similar conditions, Pd or Ni catalysts induced oxidative homocoupling of 1 to yield biaryls instead. The beneficial catalysis by Rh in the carbonylation was presumed to stem from the facility by which the migration of the aryl ligand to CO at the Rh(3+) intermediate occurred.
RESUMEN
The catalytic cross-coupling between ArZnX and ICH(2)(CH(2))(n)P(O)(OEt)(2) (n = 0-3) has been investigated to determine the utility of the Rh catalyst during the alkyl-aryl cross-coupling and to develop a new synthetic method for phosphoryl-substituted alkylarenes. Rh-dppf exhibits an excellent catalytic activity for the reaction with the alkylphosphonate of n = 1, whereas for the reaction with those of n = 2 or 3, beta-hydride elimination mainly takes place. As for the reaction with an alkylphosphonate of n = 0, a polarity inversion of the coupling components is necessary in order to provide the coupling products; the phosphoryl analogue of the Reformatsky reagent and ArI give the cross-coupling products in good yields through the catalysis by Rh-dppf.