# Audio-Driven Talking Head Generation — Data

来源：https://www.kaggle.com/competitions/audio-driven-talking-head-generation/data

采集时间：2026-10-19T07:51:18Z

Our talking head dataset contains **10 videos**, where each video contains a single speaker. These videos are in different languages and all the videos last for at least two minutes with a resolution of 512×512. 

- For the **Single image setting**, the first frame of each video's testing set is selected as the driving image.
- For the **video setting**, about 9/10 of the videos are given as the training set.

We choose the last 1/10 of the video to be the testing set. The audio of the testing set will be released for participants to generate their results for both the image and video settings.

Training videos and testing audios for video setting are in **Video.zip** while driving images and testing audios for single image setting are in **Single_Image.zip**.

We've also uploaded the **ground-truth camera poses** for testing set so that the PNSR and SSIM metrics would be more effective. The camera poses are generated following the convention of AD-NeRF. Please raise an issue in the discussion if you have any questions related to the dataset.