Corpus ID: 218863110

NAUTILUS: a Versatile Voice Cloning System

@article{Luong2020NAUTILUSAV,
  title={NAUTILUS: a Versatile Voice Cloning System},
  author={Hieu-Thi Luong and Junichi Yamagishi},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.11004}
}
  • Hieu-Thi Luong, Junichi Yamagishi
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • We introduce a novel speech synthesis system, called NAUTILUS, that can generate speech with a target voice either from a text input or a reference utterance of an arbitrary source speaker. By using a multi-speaker speech corpus to train all requisite encoders and decoders in the initial training stage, our system can clone unseen voices using untranscribed speech of target speakers on the basis of the backpropagation algorithm. Moreover, depending on the data circumstance of the target speaker… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 75 REFERENCES

    Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech

    VIEW 6 EXCERPTS

    Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Voice Cloning with a Few Samples

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Phonetic posteriorgrams for many-to-one voice conversion without parallel data training

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Sample Efficient Adaptive Text-to-Speech

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes

    VIEW 1 EXCERPT

    ATTS2S-VC: Sequence-to-sequence Voice Conversion with Attention and Context Preservation Mechanisms

    VIEW 1 EXCERPT