LRS2
收藏arXiv2025-09-30 收录
下载链接：
https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrs2.html
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了从BBC电视节目中提取的224小时音频视觉转写数据，用于验证该方法的有效性。数据集的规模属于中等，其任务是对音频视觉语音进行识别。
This dataset, which contains 224 hours of audiovisual transcribed data extracted from BBC television programs, is designed to validate the effectiveness of this method. It is of moderate scale, and its core task is audiovisual speech recognition.
提供机构：
University of Oxford
