Supercuts [⧉✂︎|>]
Reconstructing Video Through
Word-Level ML Segmentation

Type
Video Art, Creative Coding

Technologies
Machine Learning, Python

Supported by 
Goldsmiths, University of London

Supercut interpolation of Nina Simone performing 'I wish'. Original video can be found here. 

Supercut interpolation of Rosalía performing 'La Llorona'. Original video can be found here. 

Supercut interpolation of Johnny Cash's video for 'Hurt'. Original video can be found here. 

Supercut interpolation of Camarón performing 'Por Tangos'. Original video can be found here. 

Project Description

This project explores video segmentation and reassembly using machine learning and generative techniques.

Starting with a source video, I use a speech-to-text model to generate a word-level transcript. Each word is then isolated into a separate video clip using precise timecodes.

From there, I’ve experimented with two recomposition strategies.

1. Text-Based Reconstruction. A new sequence of words is generated to define an edit of the video by assembling the matching clips in that order.
2. Intensity-Based Sorting. Using audio RMS amplitude, each clip is assigned a rough loudness value. A separate cut is generated by sorting the clips along an intensity curve.

Digital designer and technologist based in London

For project enquiries:
antoniomdenuevo@gmail.com