Neural Percussive Synthesis Parameterised by High-Level Timbral Features

@article{Ramires2019NeuralPS,
  title={Neural Percussive Synthesis Parameterised by High-Level Timbral Features},
  author={Ant'onio Ramires and Pritish Chandna and Xavier Favory and Emilia G{\'o}mez and Xavier Serra},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.11853}
}
  • Ant'onio Ramires, Pritish Chandna, +2 authors Xavier Serra
  • Published 2019
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • We present a deep neural network-based methodology for synthesising percussive sounds with control over high-level timbral characteristics of the sounds. This approach allows for intuitive control of a synthesizer, enabling the user to shape sounds without extensive knowledge of signal processing. We use a feedforward convolutional neural network-based architecture, which is able to map input parameters to the corresponding waveform. We propose two datasets to evaluate our approach on both a… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural drum machine : An interactive system for realtime synthesis

    • Cyran Aouameur, Philippe Esling, Gaëtan Hadjeres
    • 2019.
    • 2019
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Freesound technical demo

    VIEW 3 EXCERPTS

    GANSynth: Adversarial Neural Audio Synthesis

    VIEW 3 EXCERPTS

    Spectrogram Feature Losses for Music Source Separation

    VIEW 1 EXCERPT

    WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN

    VIEW 2 EXCERPTS