• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Harmonic-percussive source separation with deep neural networks and phase recovery
 
  • Details
  • Full
Options
2018
Conference Paper
Title

Harmonic-percussive source separation with deep neural networks and phase recovery

Abstract
Harmonic/percussive source separation (HPSS) consists in separating the pitched instruments from the percussive parts in a music mixture. In this paper, we propose to apply the recently introduced Masker-Denoiser with twin networks (MaD TwinNet) system to this task. MaD TwinNet is a deep learning architecture that has reached state-of-the-art results in monaural singing voice separation. Herein, we propose to apply it to HPSS by using it to estimate the magnitude spectrogram of the percussive source. Then, we retrieve the complex-valued short-time Fourier transform of the sources by means of a phase recovery algorithm, which minimizes the reconstruction error and enforces the phase of the harmonic part to follow a sinusoidal phase model. Experiments conducted on realistic music mixtures show that this novel separation system outperforms the previous state-of-the art kernel additive model approach.
Author(s)
Mimilakis, S.I.  
Drossos, K.
Magron, P.
Virtanen, T.
Mainwork
16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018. Proceedings  
Conference
International Workshop on Acoustic Signal Enhancement (IWAENC) 2018  
Open Access
DOI
10.1109/IWAENC.2018.8521371
Language
English
Fraunhofer-Institut für Digitale Medientechnologie IDMT  
Keyword(s)
  • Automatic Music Analysis

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024