C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model

doi:doi:10.57702/6acjrrad

C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model

Co-speech gesture generation is crucial for automatic digital avatar animation. However, existing methods suffer from issues such as unstable training and temporal inconsistency, particularly in generating high-fidelity and comprehensive gestures. Additionally, these methods lack effective control over speaker identity and temporal editing of the generated gestures.

BibTex:

@dataset{Longbin_Ji_and_Pengfei_Wei_and_Yi_Ren_and_Jinglin_Liu_and_Chen_Zhang_and_Xiang_Yin_2024,
    abstract = {Co-speech gesture generation is crucial for automatic digital avatar animation. However, existing methods suffer from issues such as unstable training and temporal inconsistency, particularly in generating high-fidelity and comprehensive gestures. Additionally, these methods lack effective control over speaker identity and temporal editing of the generated gestures.},
    author = {Longbin Ji and Pengfei Wei and Yi Ren and Jinglin Liu and Chen Zhang and Xiang Yin},
    doi = {10.57702/6acjrrad},
    institution = {No Organization},
    keyword = {'co-speech gesture generation', 'latent diffusion model', 'speaker identity', 'temporal editing'},
    month = {dec},
    publisher = {TIB},
    title = {C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model},
    url = {https://service.tib.eu/ldmservice/dataset/c2g2--controllable-co-speech-gesture-generation-with-latent-diffusion-model},
    year = {2024}
}