Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

New sonorities for jazz recordings: Separation and mixing using deep neural networks

 
: Mimilakis, Stylianos-Ioannis; Cano, Estefanía; Abeßer, Jakob; Schuller, Gerald

:
Fulltext (PDF; )

Man, B. de ; Audio Engineering Society -AES-:
2nd Workshop on Intelligent Music Production 2016. Proceedings. Online resource : 13 September 2016, London
London, 2016
http://www.aes-uk.org/forthcoming-meetings/wimp2/#proceedings
2 pp.
Workshop on Intelligent Music Production <2, 2016, London>
English
Conference Paper, Electronic Publication
Fraunhofer IDMT ()

Abstract
The audio mixing process is an art that has proven to be extremely hard to model: What makes a certain mix better than another one? How can the mixing processing chain be automatically optimized to obtain better results in a more efficient manner? Over the last years, the scientific community has exploited methods from signal processing, music information retrieval, machine learning, and more recently, deep learning techniques to address these issues. In this work, a novel system based on deep neural networks (DNNs) is presented. It replaces the previously proposed steps of pitch-informed source separation and panoramabased remixing by an ensemble of trained DNNs.

: http://publica.fraunhofer.de/documents/N-435951.html