Stephen Downes

Knowledge, Learning, Community

In a world where deepfakes videos are a real thing, it's not surprising to read that researchers have developed software that can create a video lecture from an audio narration (though one wonders: why?). In an arXiv preprint (9 page PDF) researchers Byung-Hak Kim and Varun Ganapathi "present LumièreNet, a simple, modular, and completely deep-learning based architecture that synthesizes high quality, full-pose headshot lecture videos from instructor's new audio narration of any length." This article summarizes the paper. 

Today: 1 Total: 62 [Direct link]

files/images/udacity-e1562335811374.png


Stephen Downes Stephen Downes, Casselman, Canada
stephen@downes.ca

Copyright 2024
Last Updated: Feb 21, 2024 4:59 p.m.

Canadian Flag Creative Commons License.

Force:yes