Time Series Forecasting (TSF) is used in astronomy, geology, weather forecasting, and finance to name a few. Recent research [1] has shown that, combined with Machine Learning (ML) techniques, TSF can be applied successfully for short-term predictions of music signals. We present here an application of this approach for predicting audio level changes of music and appropriate Dynamic Range Compression (DRC). This ML-based look ahead prediction of audio level allows to apply compression just-in-time, avoiding latency and attack/release time constants, which are proper to traditional DRC and challenging to tune.

Authors: Brunet, Pascal; Li, Yuan; Kim, Soohyun
Affiliations: 27931 Smyth Drive; Samsung Research America; CCRMA- Stanford University(See document for exact affiliation information.)
Express Paper 112; AES Convention 155; October 2023
Publication Date: October 25, 2023 Import into BibTeX
Subject: Signal Processing
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=22266

Download Now (496 KB)

This paper is Open Access which means you can download it for free.

Learn more about the AES E-Library

E-Library Location:   /conv/155/112.pdf

Start a discussion about this Signal Processing!