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.
(See document for exact affiliation information.)
https://aes2.org/publications/elibrary-page/?id=22266
(496KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
