arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.04498cs.CVcs.AIeess.ASeess.IV
收藏

具有用户依赖填充的说话人自适应唇读

Speaker-adaptive Lip Reading with User-dependent Padding

KAIST(韩国科学技术院)

Minsu Kim, Hyunjun Kim, Yong Man Ro

摘要:

唇读旨在仅根据嘴唇运动来预测语音。由于它专注于视觉信息来模拟语音,因此其性能本质上对个人嘴唇外观和运动敏感。由于训练和测试条件之间的不匹配,这使得唇读模型在应用于看不见的说话者时表现出降低的性能。说话人自适应技术旨在减少训练和测试说话人之间的这种不匹配,从而引导训练模型专注于对语音内容进行建模,而不受说话人变化的干扰。相对于基于音频的语音识别几十年来的努力,唇读中的说话人自适应方法还没有得到很好的研究。针对唇读模型在未知说话人情况下的性能下降问题,提出了一种说话人自适应唇读方法,即用户相关填充。依赖于用户的填充是说话者特定的输入,其可以参与预先训练的唇读模型的视觉特征提取阶段。因此,在视觉特征编码过程中,可以考虑不同说话人的嘴唇外观和运动信息,自适应地针对单个说话人。此外,所提出的方法不需要1)任何附加层,2)修改预训练模型的学习权重,以及3)在预训练期间使用的训练数据的说话人标签。它可以直接适应看不见的扬声器,通过学习用户相关的填充,在监督或无监督的方式。最后,为了解决公共唇读数据库中说话人信息不足的问题,我们对一个著名的视听数据库LRW中的说话人进行了标记,并设计了一个名为LRW-ID的隐形说话人唇读场景。

英文摘要:

Lip reading aims to predict speech based on lip movements alone. As it focuses on visual information to model the speech, its performance is inherently sensitive to personal lip appearances and movements. This makes the lip reading models show degraded performance when they are applied to unseen speakers due to the mismatch between training and testing conditions. Speaker adaptation technique aims to reduce this mismatch between train and test speakers, thus guiding a trained model to focus on modeling the speech content without being intervened by the speaker variations. In contrast to the efforts made in audio-based speech recognition for decades, the speaker adaptation methods have not well been studied in lip reading. In this paper, to remedy the performance degradation of lip reading model on unseen speakers, we propose a speaker-adaptive lip reading method, namely user-dependent padding. The user-dependent padding is a speaker-specific input that can participate in the visual feature extraction stage of a pre-trained lip reading model. Therefore, the lip appearances and movements information of different speakers can be considered during the visual feature encoding, adaptively for individual speakers. Moreover, the proposed method does not need 1) any additional layers, 2) to modify the learned weights of the pre-trained model, and 3) the speaker label of train data used during pre-train. It can directly adapt to unseen speakers by learning the user-dependent padding only, in a supervised or unsupervised manner. Finally, to alleviate the speaker information insufficiency in public lip reading databases, we label the speaker of a well-known audio-visual database, LRW, and design an unseen-speaker lip reading scenario named LRW-ID.

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。

↑