Analysis and Prediction of the Audio Feature Space when Mixing Raw Recordings into Individual Stems

Martinez Ramirez MA, Reiss JD. Analysis and Prediction of the Audio Feature Space when Mixing Raw Recordings into Individual Stems. In: AES Convention 143. Audio Engineering Society; 2017. Paper 9848. Available from: https://aes.org/publications/elibrary-page/?id=19245

@inproceedings{MartinezRamirez2017_19245,
  author = {Martinez Ramirez, Marco A. and Reiss, Joshua D.},
  title = {{Analysis and Prediction of the Audio Feature Space when Mixing Raw Recordings into Individual Stems}},
  booktitle = {AES Convention 143},
  note = {Paper 9848},
  year = {2017},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19245}
}

TY  - CPAPER
TI  - Analysis and Prediction of the Audio Feature Space when Mixing Raw Recordings into Individual Stems
AU  - Martinez Ramirez, Marco A.
AU  - Reiss, Joshua D.
T2  - AES Convention 143
M1  - Paper 9848
PY  - 2017
DA  - 2017/10/06
UR  - https://aes.org/publications/elibrary-page/?id=19245
PB  - Audio Engineering Society
LA  - en
AB  - Processing individual stems from raw recordings is one of the first steps of multitrack audio mixing. In this work we explore which set of low-level audio features are sufficient to design a prediction model for this transformation. We extract a large set of audio features from bass, guitar, vocal, and keys raw recordings and stems. We show that a procedure based on random forests classifiers can lead us to reduce significantly the number of features and we use the selected audio features to train various multi-output regression models. Thus, we investigate stem processing as a content-based transformation, where the inherent content of raw recordings leads us to predict the change of feature values that occurred within the transformation.
ER  -