Auto-adaptive Resonance Equalization using Dilated Residual Networks

Abstract:In music and audio production, attenuation of spectral resonances is an important step towards a technically correct result. In this paper we present a two-component system to automate the task of resonance equalization. The first component is a dynamic equalizer that automatically detects resonances and offers to attenuate them by a user-specified factor. The second component is a deep neural network that predicts the optimal attenuation factor based on the windowed audio. The network is trained and validated on empirical data gathered from an experiment in which sound engineers choose their preferred attenuation factors for a set of tracks. We test two distinct network architectures for the predictive model and find that a dilated residual network operating directly on the audio signal is on a par with a network architecture that requires a prior audio feature extraction stage. Both architectures predict human-preferred resonance attenuation factors significantly better than a baseline approach.

Sound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)

arXiv:1807.08636 [cs.SD]

(or arXiv:1807.08636v2 [cs.SD] for this version)

https://doi.org/10.48550/arXiv.1807.08636 Focus to learn more arXiv-issued DOI via DataCite

Proceedings of the 20th ISMIR Conference, Delft, Netherlands, November 4-8, 2019. Pp. 405-411. https://archives.ismir.net/ismir2019/paper/000048.pdf

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.