基于跨语言领域自适应和侧抑制的罗马尼亚语端到端唇读
End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition
AI总结：
针对罗马尼亚语唇读数据不足的问题，本文在 Wild LRRo 上比较多种架构与正则化后端，并利用英语、德语未标注视频进行跨语言领域自适应，加入神经侧抑制层，取得当前最优结果。
摘要：
唇读（即视觉语音识别）近年来受到广泛关注，这尤其得益于硬件发展和计算机视觉领域的创新。尽管该领域已取得显著进展，但大多数模型仅在少数大规模数据集上进行了测试。本工作针对这一不足，在代表性不足、规模较小的罗马尼亚语数据集 Wild LRRo 上分析了多种架构和优化方法。最值得注意的是，我们比较了不同的后端模块，证明了加入充分正则化方法的有效性。通过所提出的方法，我们取得了当前最优结果，即利用跨语言领域自适应以及来自英语和德语数据集的未标注视频，帮助模型学习语言不变特征。最后，我们评估了加入一个受神经抑制机制启发的层后的性能。
英文摘要：
Lip reading or visual speech recognition has gained significant attention in recent years, particularly because of hardware development and innovations in computer vision. While considerable progress has been obtained, most models have only been tested on a few large-scale datasets. This work addresses this shortcoming by analyzing several architectures and optimizations on the underrepresented, short-scale Romanian language dataset called Wild LRRo. Most notably, we compare different backend modules, demonstrating the effectiveness of adding ample regularization methods. We obtain state-of-the-art results using our proposed method, namely cross-lingual domain adaptation and unlabeled videos from English and German datasets to help the model learn language-invariant features. Lastly, we assess the performance of adding a layer inspired by the neural inhibition mechanism.
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。
