Feature Design Using Audio Decomposition for Intelligent Control of the Dynamic Range Compressor

This papeper proposes a method of controlling the dynamic range compressor using sound examples. Our earlier work showed the effectiveness of random forest regression to map acoustic features to effect control parameters [1]. We extend this work to address the challenging task of extracting relevant features when audio events overalp. We assess different audio decomposition approaches suchs as onset event detection, NMF, and transient/stationary audio separation using ISTA and compare feature extraction strategies for each case. Numerical and perceptual similarty tests show the utility of audio decomposition as well as specific features in the prediction of dynamic range compressor parameters.