Corpus ID: 14254027

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

@article{Mehri2017SampleRNNAU,
  title={SampleRNN: An Unconditional End-to-End Neural Audio Generation Model},
  author={Soroush Mehri and K. Kumar and Ishaan Gulrajani and Rithesh Kumar and Shubham Jain and J. Sotelo and Aaron C. Courville and Yoshua Bengio},
  journal={ArXiv},
  year={2017},
  volume={abs/1612.07837}
}
  • Soroush Mehri, K. Kumar, +5 authors Yoshua Bengio
  • Published 2017
  • Computer Science
  • ArXiv
  • In this paper we propose a novel model for unconditional audio generation task that generates one audio sample at a time. [...] Key Result We also show how each component of the model contributes to the exhibited performance.Expand Abstract
    320 Citations

    Figures, Tables, and Topics from this paper.

    MelNet: A Generative Model for Audio in the Frequency Domain
    • 43
    • PDF
    Char2Wav: End-to-End Speech Synthesis
    • 275
    • PDF
    Tacotron: Towards End-to-End Speech Synthesis
    • 594
    • Highly Influenced
    • PDF
    Multi-speaker Neural Vocoder
    • 1
    • Highly Influenced
    • PDF
    A general-purpose deep learning approach to model time-varying audio effects
    • 4
    • PDF
    SING: Symbol-to-Instrument Neural Generator
    • 18
    • Highly Influenced
    • PDF
    DiffWave: A Versatile Diffusion Model for Audio Synthesis
    • 3
    • Highly Influenced
    • PDF
    Waveform Modeling and Generation Using Hierarchical Recurrent Neural Networks for Speech Bandwidth Extension
    • 27
    • Highly Influenced
    • PDF
    Excitation-by-SampleRNN Model for Text-to-Speech

    References

    SHOWING 1-10 OF 32 REFERENCES
    WaveNet: A Generative Model for Raw Audio
    • 3,009
    • Highly Influential
    • PDF
    Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
    • 4,904
    • PDF
    A Recurrent Latent Variable Model for Sequential Data
    • 592
    • PDF
    A Clockwork RNN
    • 313
    • Highly Influential
    • PDF
    Generating Sequences With Recurrent Neural Networks
    • 2,482
    • PDF
    An Empirical Exploration of Recurrent Network Architectures
    • 1,116
    • PDF
    Unsupervised feature learning for audio classification using convolutional deep belief networks
    • 995
    • PDF
    Learning Complex, Extended Sequences Using the Principle of History Compression
    • 371
    • Highly Influential
    Pixel Recurrent Neural Networks
    • 1,276
    • Highly Influential
    • PDF