Corpus ID: 67856213

GANSynth: Adversarial Neural Audio Synthesis

@article{Engel2019GANSynthAN,
  title={GANSynth: Adversarial Neural Audio Synthesis},
  author={J. Engel and Kumar Krishna Agrawal and S. Chen and Ishaan Gulrajani and Chris Donahue and Adam Roberts},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.08710}
}
  • J. Engel, Kumar Krishna Agrawal, +3 authors Adam Roberts
  • Published 2019
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. [...] Key Result Through extensive empirical investigations on the NSynth dataset, we demonstrate that GANs are able to outperform strong WaveNet baselines on automated and human evaluation metrics, and efficiently generate audio several orders of magnitude faster than their autoregressive counterparts.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Adversarial Audio Synthesis
    • 141
    • PDF
    MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
    • 67
    • PDF
    Comparing Representations for Audio Synthesis Using Generative Adversarial Networks
    • 1
    • Highly Influenced
    • PDF
    Adversarial Generation of Time-Frequency Features with application in audio synthesis
    • 19
    • Highly Influenced
    • PDF
    HIGH FIDELITY SPEECH SYNTHESIS
    High Fidelity Speech Synthesis with Adversarial Networks
    • 30
    • PDF
    DDSP: Differentiable Digital Signal Processing
    • 25
    • PDF
    Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
    • 1
    • PDF
    Self-supervised Pitch Detection by Inverse Audio Synthesis
    MelNet: A Generative Model for Audio in the Frequency Domain
    • 39
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES
    Adversarial Audio Synthesis
    • 141
    • PDF
    Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
    • 222
    • PDF
    Large Scale GAN Training for High Fidelity Natural Image Synthesis
    • 1,195
    • PDF
    WaveNet: A Generative Model for Raw Audio
    • 2,809
    • PDF
    SING: Symbol-to-Instrument Neural Generator
    • 15
    • PDF
    Improved Training of Wasserstein GANs
    • 3,353
    • PDF
    SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
    • 300
    • PDF
    A Style-Based Generator Architecture for Generative Adversarial Networks
    • 1,163
    • Highly Influential
    • PDF
    Conditional Image Synthesis with Auxiliary Classifier GANs
    • 1,349
    • PDF