@inproceedings{8baf0113899b4fb7b7bcd444932c0920,
title = "End to end lip synchronization with a temporal autoencoder",
abstract = "We study the problem of syncing the lip movement in a video with the audio stream. Our solution finds an optimal alignment using a dual-domain recurrent neural network that is trained on synthetic data we generate by dropping and duplicating video frames. Once the alignment is found, we modify the video in order to sync the two sources. Our method is shown to greatly outperform the literature methods on a variety of existing and new benchmarks. As an application, we demonstrate our ability to robustly align text-to-speech generated audio with an existing video stream. Our code is attached as supplementary.",
author = "Yoav Shalev and Lior Wolf",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 ; Conference date: 01-03-2020 Through 05-03-2020",
year = "2020",
month = mar,
doi = "https://doi.org/10.1109/WACV45572.2020.9093490",
language = "الإنجليزيّة",
series = "Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "330--339",
booktitle = "Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020",
address = "الولايات المتّحدة",
}