Sorry, you need to enable JavaScript to visit this website.

FEATURE DESIGN USING AUDIO DECOMPOSITION FOR INTELLIGENT CONTROL OF THE DYNAMIC RANGE COMPRESSOR

Citation Author(s):
Di Sheng, Gyorgy Fazekas
Submitted by:
Di Sheng
Last updated:
12 April 2018 - 1:40pm
Document Type:
Poster
Document Year:
2018
Event:
Presenters:
Di Sheng
Paper Code:
ICASSP18001
 

This paper 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. We extend this work to address the challenging task of extracting relevant features when audio events overlap. We assess differ- ent audio decomposition approaches such as onset event detection, NMF, and transient/stationary audio separation using ISTA and compare feature extraction strategies for each case. Numerical and perceptual similarity tests show the utility of audio decomposition as well as specific features in the prediction of dynamic range compressor parameters.

up
0 users have voted: