Cerebella: Automatic Generation of Nonverbal Behavior for Virtual Humans
Authors: Margot Lhommet, Yuyu Xu, Stacy Marsella
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our method automatically generates realistic nonverbal performances for virtual characters to accompany spoken utterances. It analyses the acoustic, syntactic, semantic and rhetorical properties of the utterance text and audio signal to generate nonverbal behavior such as such as head movements, eye saccades, and novel gesture animations based on co-articulation. ... Specifically, we demonstrate the automatic generation of a character s nonverbal behavior from the audio and text of the dialog they must speak. |
| Researcher Affiliation | Academia | Margot Lhommet and Yuyu Xu and Stacy Marsella Northeastern University 360 Huntington Avenue Boston, MA, 02115 |
| Pseudocode | No | The paper describes a "Generation Pipeline" with numbered steps, but these steps are descriptive and not formatted as structured pseudocode or an algorithm block. |
| Open Source Code | No | The paper mentions an "interactive demonstration" but does not provide concrete access to the source code for the methodology described in the paper. |
| Open Datasets | No | The paper describes processing input audio and text for the system but does not provide concrete access information (e.g., specific link, DOI, repository name, or formal citation) for a publicly available or open dataset used for training. |
| Dataset Splits | No | The paper does not provide specific dataset split information (e.g., exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments or demonstrations. |
| Software Dependencies | No | The paper mentions "Smartbody (Thiebaux et al. 2008)" and "Virtual Human Toolkit (Hartholt et al. 2013)" but does not provide specific version numbers for these or any other ancillary software components. |
| Experiment Setup | No | The paper describes the high-level steps of the "Generation Pipeline" but does not contain specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings in the main text. |