Deep neural network based instrument extraction from music

This paper deals with the extraction of an instrument from music by using a deep neural network. As prior information, we only assume to know the instrument types that are present in the mixture and, using this information, we generate the training data from a database with solo instrument performan...

Full description

Saved in:
Bibliographic Details
Main Authors: Uhlich, Stefan, Giron, Franck, Mitsufuji, Yuki
Format: Conference Proceeding
Language:English
Subjects:
Blind source separation (BSS)
Deep neural network (DNN)
Instrument extraction
Instruments
MATLAB
Mel frequency cepstral coefficient
Multiple signal classification
RNA
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper deals with the extraction of an instrument from music by using a deep neural network. As prior information, we only assume to know the instrument types that are present in the mixture and, using this information, we generate the training data from a database with solo instrument performances. The neural network is built up from rectified linear units where each hidden layer has the same number of nodes as the output layer. This allows a least squares initialization of the layer weights and speeds up the training of the network considerably compared to a traditional random initialization. We give results for two mixtures, each consisting of three instruments, and evaluate the extraction performance using BSS Eval for a varying number of hidden layers.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2015.7178348