University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Estimating the loudness balance of musical mixtures using audio source separation

Ward, Dominic, Wierstorf, Hagen, Mason, Russell, Plumbley, Mark and Hummersone, Christopher (2017) Estimating the loudness balance of musical mixtures using audio source separation In: 3rd Workshop on Intelligent Music Production, (WIMP 2017), 15 September, 2017, Salford, UK.

Ward2017.pdf - Version of Record

Download (315kB) | Preview


To assist with the development of intelligent mixing systems, it would be useful to be able to extract the loudness balance of sources in an existing musical mixture. The relative-to-mix loudness level of four instrument groups was predicted using the sources extracted by 12 audio source separation algorithms. The predictions were compared with the ground truth loudness data of the original unmixed stems obtained from a recent dataset involving 100 mixed songs. It was found that the best source separation system could predict the relative loudness of each instrument group with an average root-mean-square error of 1.2 LU, with superior performance obtained on vocals.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Date : 15 September 2017
Funders : EPSRC
Copyright Disclaimer : This is an Open Access paper, licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Related URLs :
Depositing User : Melanie Hughes
Date Deposited : 18 Aug 2017 08:57
Last Modified : 11 Dec 2018 11:23

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800