A Machine-Learning Approach to Application of Intelligent Artificial Reverberation

Chourdakis ET, Reiss JD. A Machine-Learning Approach to Application of Intelligent Artificial Reverberation. J Audio Eng Soc. 2017;65(1/2):56-65. doi:10.17743/jaes.2016.0069

@article{Chourdakis2017_18543,
  author = {Chourdakis, Emmanouil T. and Reiss, Joshua D.},
  title = {{A Machine-Learning Approach to Application of Intelligent Artificial Reverberation}},
  journal = {Journal of the Audio Engineering Society},
  volume = {65},
  number = {1/2},
  pages = {56--65},
  year = {2017},
  month = jan,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2016.0069},
  url = {https://doi.org/10.17743/jaes.2016.0069}
}

TY  - JOUR
TI  - A Machine-Learning Approach to Application of Intelligent Artificial Reverberation
AU  - Chourdakis, Emmanouil T.
AU  - Reiss, Joshua D.
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 65
IS  - 1/2
SP  - 56
EP  - 65
PY  - 2017
DA  - 2017/01/06
DO  - 10.17743/jaes.2016.0069
UR  - https://doi.org/10.17743/jaes.2016.0069
PB  - Audio Engineering Society
LA  - en
AB  - Digital audio effects, such as adding artificial reverberation, are actually transformations on an audio signal, where the transformation depends on a set of control parameters. Users change parameters over time based on the resulting perceived sound. This research simulates the process of automating the parameters using supervised learning to train classifiers so that they automatically assign effect parameter sets to audio features. Training can be done a-priori, as for example, by an expert user of the reverberation effects, or online by the user of such an effect. An automatic reverberator trained on a set of audio is expected to be able to apply reverberation correctly on similar audio defined by such properties as timbre, tempo, etc. For this reason, in order to create a reverberation effect that is as general as possible, training requires a large and diverse set of audio data. In one investigation, the user provides monophonic examples of desired reverberation characteristics for individual tracks taken from the Open Multitrack Testbed. This data was used to train a set of models that will automatically apply reverberation to similar tracks. The model was evaluated using classifier f1-scores, mean squared errors, and multistimulus listening tests. The best features from a 31-dimensional feature space were used.
ER  -