Feature Selection for Dynamic Range Compressor Parameter Estimation
×
Cite This
Citation & Abstract
D. Sheng, and G. Fazekas, "Feature Selection for Dynamic Range Compressor Parameter Estimation," Paper 9997, (2018 May.). doi:
D. Sheng, and G. Fazekas, "Feature Selection for Dynamic Range Compressor Parameter Estimation," Paper 9997, (2018 May.). doi:
Abstract: Casual users of audio effects may lack practical experience or knowledge of their low-level signal processing parameters. An intelligent control tool that allows using sound examples to control effects would strongly benefit these users. In a previous work we proposed a control method for the dynamic range compressor (DRC) using a random forest regression model. It maps audio features extracted from a reference sound to DRC parameter values, such that the processed signal resembles the reference. The key to good performance in this system is the relevance and effectiveness of audio features. This paper focusses on a thorough exposition and assessment of the features, as well as the comparison of different strategies to find the optimal feature set for DRC parameter estimation, using automatic feature selection methods. This enables us to draw conclusions about which features are relevant to core DRC parameters. Our results show that conventional time and frequency domain features well known from the literature are sufficient to estimate the DRC's threshold and ratio parameters, while more specialized features are needed for attack and release time, which induce more subtle changes to the signal.
@article{sheng2018feature,
author={sheng, di and fazekas, györgy},
journal={journal of the audio engineering society},
title={feature selection for dynamic range compressor parameter estimation},
year={2018},
volume={},
number={},
pages={},
doi={},
month={may},}
@article{sheng2018feature,
author={sheng, di and fazekas, györgy},
journal={journal of the audio engineering society},
title={feature selection for dynamic range compressor parameter estimation},
year={2018},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={casual users of audio effects may lack practical experience or knowledge of their low-level signal processing parameters. an intelligent control tool that allows using sound examples to control effects would strongly benefit these users. in a previous work we proposed a control method for the dynamic range compressor (drc) using a random forest regression model. it maps audio features extracted from a reference sound to drc parameter values, such that the processed signal resembles the reference. the key to good performance in this system is the relevance and effectiveness of audio features. this paper focusses on a thorough exposition and assessment of the features, as well as the comparison of different strategies to find the optimal feature set for drc parameter estimation, using automatic feature selection methods. this enables us to draw conclusions about which features are relevant to core drc parameters. our results show that conventional time and frequency domain features well known from the literature are sufficient to estimate the drc's threshold and ratio parameters, while more specialized features are needed for attack and release time, which induce more subtle changes to the signal.},}
TY - paper
TI - Feature Selection for Dynamic Range Compressor Parameter Estimation
SP -
EP -
AU - Sheng, Di
AU - Fazekas, György
PY - 2018
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2018
TY - paper
TI - Feature Selection for Dynamic Range Compressor Parameter Estimation
SP -
EP -
AU - Sheng, Di
AU - Fazekas, György
PY - 2018
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2018
AB - Casual users of audio effects may lack practical experience or knowledge of their low-level signal processing parameters. An intelligent control tool that allows using sound examples to control effects would strongly benefit these users. In a previous work we proposed a control method for the dynamic range compressor (DRC) using a random forest regression model. It maps audio features extracted from a reference sound to DRC parameter values, such that the processed signal resembles the reference. The key to good performance in this system is the relevance and effectiveness of audio features. This paper focusses on a thorough exposition and assessment of the features, as well as the comparison of different strategies to find the optimal feature set for DRC parameter estimation, using automatic feature selection methods. This enables us to draw conclusions about which features are relevant to core DRC parameters. Our results show that conventional time and frequency domain features well known from the literature are sufficient to estimate the DRC's threshold and ratio parameters, while more specialized features are needed for attack and release time, which induce more subtle changes to the signal.
Casual users of audio effects may lack practical experience or knowledge of their low-level signal processing parameters. An intelligent control tool that allows using sound examples to control effects would strongly benefit these users. In a previous work we proposed a control method for the dynamic range compressor (DRC) using a random forest regression model. It maps audio features extracted from a reference sound to DRC parameter values, such that the processed signal resembles the reference. The key to good performance in this system is the relevance and effectiveness of audio features. This paper focusses on a thorough exposition and assessment of the features, as well as the comparison of different strategies to find the optimal feature set for DRC parameter estimation, using automatic feature selection methods. This enables us to draw conclusions about which features are relevant to core DRC parameters. Our results show that conventional time and frequency domain features well known from the literature are sufficient to estimate the DRC's threshold and ratio parameters, while more specialized features are needed for attack and release time, which induce more subtle changes to the signal.
Authors:
Sheng, Di; Fazekas, György
Affiliation:
Queen Mary University of London, London, UK
AES Convention:
144 (May 2018)
Paper Number:
9997
Publication Date:
May 14, 2018Import into BibTeX
Subject:
Audio Processing and Effects – Part 1
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=19514