A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment

Tomi Kinnunen, Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio, Zhenhua Ling


Voice conversion (VC) aims at conversion of speaker characteristic without altering content. Due to training data limitations and modeling imperfections, it is difficult to achieve believable speaker mimicry without introducing processing artifacts; performance assessment of VC, therefore, usually involves both speaker similarity and quality evaluation by a human panel. As a time-consuming, expensive, and non-reproducible process, it hinders rapid prototyping of new VC technology. We address quality assessment using an alternative, objective approach leveraging from prior work on spoofing countermeasures (CMs) for automatic speaker verification. Therein, CMs are used for rejecting `fake' inputs such as replayed, synthetic or converted speech but their potential for speech quality assessment remains unknown. This study serves to fill that gap. As a supplement to subjective results for the 2018 Voice Conversion Challenge (VCC'18) data, we configure a standard constant-Q cepstral coefficient CM to quantify the extent of processing artifacts. Equal error rate (EER) of the CM, a confusability index of VC samples with real human speech, serves as our quality measure. Two clusters of VCC'18 entries are identified: low-quality ones (low EERs), and higher quality ones that are more confusable with real human speech. None of the VCC'18 systems, however, is perfect: all EERs are $<30\%$ (the `ideal' value would be 50%). Our preliminary findings suggest potential of CMs outside of their original application, as a supplemental optimization and benchmarking tool to enhance VC technology.


 DOI: 10.21437/Odyssey.2018-27

Cite as: Kinnunen, T., Lorenzo-Trueba, J., Yamagishi, J., Toda, T., Saito, D., Villavicencio, F., Ling, Z. (2018) A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment . Proc. Odyssey 2018 The Speaker and Language Recognition Workshop, 187-194, DOI: 10.21437/Odyssey.2018-27.


@inproceedings{Kinnunen2018,
  author={Tomi Kinnunen and Jaime Lorenzo-Trueba and Junichi Yamagishi and Tomoki Toda and Daisuke Saito and Fernando Villavicencio and Zhenhua Ling},
  title={A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment	},
  year=2018,
  booktitle={Proc. Odyssey 2018 The Speaker and Language Recognition Workshop},
  pages={187--194},
  doi={10.21437/Odyssey.2018-27},
  url={http://dx.doi.org/10.21437/Odyssey.2018-27}
}