Parallel Stacked Hourglass Network for Music Source Separation
Open Access
- 12 November 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 206016-206027
Abstract
Music source separation is one of the old and challenging problems in music information retrieval society. Improvements in deep learning lead to big progress in decomposing music into its constitutive components with a variety of music. This research uses three types of datasets for source separation namely; Korean traditional music Pansori dataset, MIR-1K dataset, and DSD100 dataset. DSD100 dataset includes multiple sound sources and other two datasets has relatively smaller number of sound sources. We synthetically constructed a novel dataset for Pansori music and trained a novel parallel stacked hourglass network (PSHN) with multiple band spectrograms. In comparison with past study, proposed architecture performs the best results in real-world test samples of Pansori music of any length. The network performance was also tested for the public DSD100 and MIR-1K dataset for strength comparison in multiple source data and found comparable quantitative and qualitative outcomes. System performance is evaluated using median value of signal-to-distortion ratio (SDR), source-to-interference ratio (SIR), and source-to-artifacts ratio (SAR) measured in decibels (dB) and visual comparison of prediction results with ground truth. We report better performance in the Pansori dataset and MIR-1K dataset and perform detailed ablation studies based on architecture variation. The proposed system is better applicable for separating the music source with voices and single or fewer musical instruments.Keywords
Funding Information
- Human Resources Program in Energy Technology of the Korea Institute of Energy Technology Evaluation and Planning KETEP (20204010600470)
- Jeonbuk National University
This publication has 28 references indexed in Scilit:
- Multichannel Audio Source Separation With Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Discriminative deep recurrent neural networks for monaural speech separation2016
- Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Deep neural network based instrument extraction from music2015
- Deep NMF for speech separation2015
- The 2013 Signal Separation Evaluation Campaign2013
- Using voice suppression algorithms to improve beat tracking in the presence of highly predominant vocals2013
- Using blind source separation techniques to improve speech recognition in bilateral cochlear implant patientsThe Journal of the Acoustical Society of America, 2008
- Sparse Component Analysis and Blind Source Separation of Underdetermined MixturesIEEE Transactions on Neural Networks, 2005
- Independent component analysis: algorithms and applicationsNeural Networks, 2000