{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/obamanet-photo-realistic-lip-sync-from-text","title":"ObamaNet: Photo-realistic lip-sync from text","arxiv_id":"1801.01442","date":"2017-12-06","proceeding":null,"authors":["Rithesh Kumar","Jose Sotelo","Kundan Kumar","Alexandre de Brebisson","Yoshua Bengio"],"abstract":"We present ObamaNet, the first architecture that generates both audio and\nsynchronized photo-realistic lip-sync videos from any new text. Contrary to\nother published lip-sync approaches, ours is only composed of fully trainable\nneural modules and does not rely on any traditional computer graphics methods.\nMore precisely, we use three main modules: a text-to-speech network based on\nChar2Wav, a time-delayed LSTM to generate mouth-keypoints synced to the audio,\nand a network based on Pix2Pix to generate the video frames conditioned on the\nkeypoints.","url_abs":"http://arxiv.org/abs/1801.01442v1","url_pdf":"http://arxiv.org/pdf/1801.01442v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"obamanet-photo-realistic-lip-sync-from-text","repo_url":"https://github.com/ung200/thats-what-obama-said","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"constrained-lip-synchronization","task_name":"Constrained Lip-synchronization"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"pix2pix","method_name":"Pix2Pix"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.01442","atlas_url":"https://app.syntology.ai/?focus=1801.01442","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}