Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask

@article{Mimilakis2018MonauralSV,
  title={Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask},
  author={S. Mimilakis and Konstantinos Drossos and J. F. Santos and G. Schuller and T. Virtanen and Yoshua Bengio},
  journal={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2018},
  pages={721-725}
}
  • S. Mimilakis, Konstantinos Drossos, +3 authors Yoshua Bengio
  • Published 2018
  • Computer Science, Engineering
  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Singing voice separation based on deep learning relies on the usage of time-frequency masking. In many cases the masking process is not a learnable function or is not encapsulated into the deep learning optimization. Consequently, most of the existing methods rely on a post processing step using the generalized Wiener filtering. This work proposes a method that learns and optimizes (during training) a source-dependent mask and does not need the aforementioned post processing step. We introduce… CONTINUE READING
    31 Citations
    MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
    • 16
    • PDF
    Unsupervised Interpretable Representation Learning for Singing Voice Separation
    • 4
    • PDF
    Reducing Interference with Phase Recovery in DNN-based Monaural Singing Voice Separation
    • 6
    • PDF
    Semi-supervised Monaural Singing Voice Separation with a Masking Network Trained on Synthetic Mixtures
    • 12
    • PDF
    Harmonic-Percussive Source Separation with Deep Neural Networks and Phase Recovery
    • 6
    • PDF
    Multichannel Singing Voice Separation by Deep Neural Network Informed DOA Constrained CMNMF
    • PDF
    Proximal Deep Recurrent Neural Network for Monaural Singing Voice Separation
    • PDF
    Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation
    • 1
    • PDF
    Examining the Mapping Functions of Denoising Autoencoders in Singing Voice Separation
    • 6

    References

    SHOWING 1-10 OF 25 REFERENCES
    A recurrent encoder-decoder approach with skip-filtering connections for monaural singing voice separation
    • 26
    • PDF
    Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
    • 304
    • PDF
    Monoaural Audio Source Separation Using Deep Convolutional Neural Networks
    • 115
    • PDF
    Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
    • 379
    • PDF
    New Sonorities for Jazz Recordings: Separation and Mixing using Deep Neural Networks
    • 17
    • PDF
    Multi-Scale multi-band densenets for audio source separation
    • 80
    • PDF
    ON THE USE OF MASKING FILTERS IN SOUND SOURCE SEPARATION
    • 21
    • PDF
    Multichannel music separation with deep neural networks
    • 59
    • PDF
    Generalized Wiener filtering with fractional power spectrograms
    • A. Liutkus, R. Badeau
    • Mathematics, Computer Science
    • 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2015
    • 82
    • Highly Influential
    • PDF