Keywords: text generation, video generation, music generation
TL;DR: We present a system for generating children story videos by using public pretrained models.
Abstract: Artistic work leveraging Machine Learning techniques is an increasingly popular endeavour for those with a creative lean. However, most work done is in a single domain: text, images, music, etc. In this work, we design a system for a machine learning created multimedia experience, specifically in the genre of children's literature. We detail the process for exclusively using publicly available pretrained deep neural network based models, we present multiple examples of the work our system creates, and we explore the problems associated in this genre of creative work.
Submission Type: archival
Presentation Type: online
Presenter: Matthew L. Olson