Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression

Brunet P, Li Y, Kim S. Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression. In: AES Convention 155. Audio Engineering Society; 2023. Paper 112. Available from: https://aes.org/publications/elibrary-page/?id=22266

@inproceedings{Brunet2023_22266,
  author = {Brunet, Pascal and Li, Yuan and Kim, Soohyun},
  title = {{Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression}},
  booktitle = {AES Convention 155},
  note = {Paper 112},
  year = {2023},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=22266}
}

TY  - CPAPER
TI  - Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression
AU  - Brunet, Pascal
AU  - Li, Yuan
AU  - Kim, Soohyun
T2  - AES Convention 155
M1  - Paper 112
PY  - 2023
DA  - 2023/10/06
UR  - https://aes.org/publications/elibrary-page/?id=22266
PB  - Audio Engineering Society
LA  - en
AB  - 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.
ER  -