{"id":11098,"date":"2026-01-19T17:58:57","date_gmt":"2026-01-19T16:58:57","guid":{"rendered":"https:\/\/satdi.umh.es\/?p=11098"},"modified":"2026-02-04T20:05:07","modified_gmt":"2026-02-04T19:05:07","slug":"un-robot-casi-humano","status":"publish","type":"post","link":"https:\/\/satdi.umh.es\/en\/2026\/01\/19\/un-robot-casi-humano\/","title":{"rendered":"A nearly human robot"},"content":{"rendered":"<p><\/p>\n<p style=\"text-align: justify\"><a href=\"https:\/\/satdi.umh.es\/files\/2026\/01\/robots2.png\"><img loading=\"lazy\" class=\"alignleft wp-image-11101 \" src=\"https:\/\/satdi.umh.es\/files\/2026\/01\/robots2-261x300.png\" alt=\"\" width=\"273\" height=\"314\" srcset=\"https:\/\/satdi.umh.es\/files\/2026\/01\/robots2-261x300.png 261w, https:\/\/satdi.umh.es\/files\/2026\/01\/robots2.png 612w\" sizes=\"(max-width: 273px) 100vw, 273px\" \/><\/a><span dir=\"auto\" style=\"vertical-align: inherit\"><span dir=\"auto\" style=\"vertical-align: inherit\">The facial movements of robots with humanoid faces have always faced a challenge: synchronizing lips and audio to appear human. Lip movement is crucial in human communication because it captures our attention. Therefore, the common desynchronization of lips and audio in robots reveals their lack of life.<\/span><\/span><\/p>\n<p style=\"text-align: justify\"><span dir=\"auto\" style=\"vertical-align: inherit\"><span dir=\"auto\" style=\"vertical-align: inherit\">A group of researchers from the <\/span><\/span><a href=\"https:\/\/www.engineering.columbia.edu\/about\/news\/robot-learns-lip-sync\" target=\"_blank\" rel=\"noopener\"><span dir=\"auto\" style=\"vertical-align: inherit\"><span dir=\"auto\" style=\"vertical-align: inherit\">Department of Computer Science at Columbia University<\/span><\/span><\/a><span dir=\"auto\" style=\"vertical-align: inherit\"><span dir=\"auto\" style=\"vertical-align: inherit\"> has unveiled a humanoid robotic face with soft silicone lips actuated by a 10-degree-of-freedom mechanism. Until now, robotic lips have typically lacked the mechanical complexity necessary to reproduce mouth movements. Furthermore, existing synchronization methods rely on manual controls, limiting their realism. This research group has used a self-supervised learning process based on a variational autoencoder (VAE), combined with a facial action transformer, enabling the robot to autonomously infer more realistic lip trajectories directly from speech audio.<\/span><\/span><\/p>\n<p style=\"text-align: justify\"><span dir=\"auto\" style=\"vertical-align: inherit\"><span dir=\"auto\" style=\"vertical-align: inherit\">Furthermore, the learned synchronization successfully generalizes across multiple linguistic contexts, enabling the robot to articulate speech in 10 languages \u200b\u200bnot encountered during training. The robot acquired this ability through observational learning, rather than by following rules. It first learned to use its 26 facial motors by observing its own reflection in the mirror, before learning to mimic human lip movements by watching hours of YouTube videos. As this is a learned skill, it will continue to improve with human interaction.<\/span><\/span><\/p>\n<p><a href=\"https:\/\/satdi.umh.es\/files\/2026\/01\/robots-1.png\"><img loading=\"lazy\" class=\"size-medium wp-image-11107 alignleft\" src=\"https:\/\/satdi.umh.es\/files\/2026\/01\/robots-1-300x193.png\" alt=\"\" width=\"300\" height=\"193\" srcset=\"https:\/\/satdi.umh.es\/files\/2026\/01\/robots-1-300x193.png 300w, https:\/\/satdi.umh.es\/files\/2026\/01\/robots-1-1024x658.png 1024w, https:\/\/satdi.umh.es\/files\/2026\/01\/robots-1-768x494.png 768w, https:\/\/satdi.umh.es\/files\/2026\/01\/robots-1.png 1383w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>The facial movements of robots with humanoid faces have always faced a challenge: synchronizing lips and audio to appear human. Lip movement is crucial in human communication because it captures our attention. Therefore, the common desynchronization of lips and audio in robots reveals their lack of life.<br \/>\nA group of researchers from the Department of Computer [&#8230;]<\/p>\n","protected":false},"author":16034,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_links_to":"","_links_to_target":""},"categories":[259,2303],"tags":[2243,4232,1494737],"_links":{"self":[{"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/posts\/11098"}],"collection":[{"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/users\/16034"}],"replies":[{"embeddable":true,"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/comments?post=11098"}],"version-history":[{"count":0,"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/posts\/11098\/revisions"}],"wp:attachment":[{"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/media?parent=11098"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/categories?post=11098"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/satdi.umh.es\/en\/wp-json\/wp\/v2\/tags?post=11098"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}