Jehan, T., Lew, M., Vaucelle, C.

Abstract

This sketch presents a real-time system that aims to bridge a gap between machine listening technology, and self-editing, selfsynchronizing video: a movie organizes itself from “listening” to music. In our current demonstration, a series of short video clips of “Cati” dancing, originally shot at different tempi, are arbitrarily sequenced, always in sync with the analyzed beat, i.e., if the music slows down, the dance slows down accordingly. When no beat is found, e.g., the music is mellow, then Cati stops dancing and waits, apparently bored