Parallel and High-Fidelity Text-to-Lip Generation

Authors: Jinglin Liu, Zhiying Zhu, Yi Ren, Wencan Huang, Baoxing Huai, Nicholas Yuan, Zhou Zhao1738-1746

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on GRID and TCD-TIMIT datasets demonstrate the superiority of proposed methods.
Researcher Affiliation Collaboration 1Zhejiang University, China 2Huawei Cloud {jinglinliu,zhyingzh,rayeren,huangwencan,zhaozhou}@zju.edu.cn, {huaibaoxing,nicholas.yuan}@huawei.com
Pseudocode No The paper includes architectural diagrams and descriptions of methods but does not provide structured pseudocode or algorithm blocks.
Open Source Code No Video samples are available via https://paralip.github.io. This link provides video samples, but the paper does not explicitly state that the source code for the methodology is available or provide a direct link to a code repository.
Open Datasets Yes GRID The GRID dataset (Cooke et al. 2006) consists of 33 video-available speakers... TCD-TIMIT The TCD-TIMIT dataset (Harte and Gillen 2015) is closer to real cases and more challenging than GRID dataset...
Dataset Splits No The paper describes training and test splits for the datasets (e.g., '255 random samples from each speaker to form the test set' for GRID and '30% of data from each speaker aside for testing' for TCD-TIMIT) but does not explicitly state information about validation dataset splits.
Hardware Specification Yes The computations are conducted on a server with 1 NVIDIA 2080Ti GPU.
Software Dependencies No The paper mentions software tools like Dlib and P2FA, but it does not provide specific version numbers for these or other software dependencies.
Experiment Setup No The paper describes its training methods and model architecture but does not provide specific hyperparameter values such as learning rate, batch size, number of epochs, or explicit values for the loss weighting hyperparameters (λ1, λ2, λ3, λ4).