arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.13403cs.CVcs.CLcs.LG
收藏

用于自动唇读系统和迁移学习的多模态德语数据集

A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning

University of Hamburg(汉堡大学)

Gerald Schwiebert, Cornelius Weber, Leyuan Qu, Henrique Siqueira, Stefan Wermter

摘要:

唇读的深度学习所需的大型数据集在许多语言中并不存在。在本文中,我们介绍了数据集GLips(德国嘴唇),由250,000个公开的黑森州议会发言人的面部视频组成,这些视频使用自动管道进行了单词级唇读处理。该格式类似于英语LRW(Lip Reading in the Wild)数据集的格式,每个视频在1.16秒的持续时间内编码一个感兴趣的单词,这为研究两个数据集之间的迁移学习提供了兼容性。通过训练深度神经网络,我们研究唇读是否具有语言无关的特征,以便不同语言的数据集可以用于改进唇读模型。我们展示了从头开始的学习,并表明从LRW到GLips的迁移学习,反之亦然,提高了学习速度和性能,特别是对于验证集。

英文摘要:

Large datasets as required for deep learning of lip reading do not exist in many languages. In this paper we present the dataset GLips (German Lips) consisting of 250,000 publicly available videos of the faces of speakers of the Hessian Parliament, which was processed for word-level lip reading using an automatic pipeline. The format is similar to that of the English language LRW (Lip Reading in the Wild) dataset, with each video encoding one word of interest in a context of 1.16 seconds duration, which yields compatibility for studying transfer learning between both datasets. By training a deep neural network, we investigate whether lip reading has language-independent features, so that datasets of different languages can be used to improve lip reading models. We demonstrate learning from scratch and show that transfer learning from LRW to GLips and vice versa improves learning speed and performance, in particular for the validation set.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑