Corpus ID: 218971878

DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices

@article{Wang2020DeepSonarTE,
  title={DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices},
  author={Run Wang and Felix Juefei-Xu and Yihao Huang and Qing Guo and Xiaofei Xie and Lei Ma and Yang Liu},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.13770}
}
  • Run Wang, Felix Juefei-Xu, +4 authors Yang Liu
  • Published 2020
  • Engineering, Computer Science
  • ArXiv
  • With the recent advances in voice synthesis such as WaveNet, AI-synthesized fake voices are indistinguishable to human ears and widely applied for producing realistic and natural DeepFakes which are real threats to everyone. However, effective and robust detectors for synthesized fake voices are still in their infancy and are not ready to fully tackle this emerging threat. In this paper, we devise a novel approach, named DeepSonar, based on monitoring neuron behaviors of speaker recognition (SR… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 60 REFERENCES

    ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Detecting AI-Synthesized Speech Using Bispectral Analysis

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems

    • Lei Ma, Felix Juefei-Xu, +9 authors Yadong Wang
    • Computer Science, Mathematics
    • 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE)
    • 2018
    VIEW 12 EXCERPTS

    TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    WaveNet: A Generative Model for Raw Audio

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    2020. libsora: audio and music processing in Python

    • Online
    • 2020

    Adversarial Examples: Attacks and Defenses for Deep Learning

    VIEW 1 EXCERPT