On Time-frequency Scattering and Computer Music

TL;DR

This paper explores the application of time-frequency scattering, a mathematical sound transformation mimicking human auditory processing, in enhancing contemporary music creation and its potential in AI-driven sound analysis.

Contribution

It demonstrates the novel use of time-frequency scattering in the context of contemporary music composition and production.

Findings

Effective in music creation processes

Improves AI analysis of musical sounds

Potential for new musical expression tools

Abstract

Time-frequency scattering is a mathematical transformation of sound waves. Its core purpose is to mimick the way the human auditory system extracts information from its environment. In the context of improving the artificial intelligence of sounds, it has found succesful applications in automatic speech transcription as well as the recognition of urban sounds and musical sounds. In this article, we show that time-frequency scattering can also be useful for applications in contemporary music creations.