Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissions
This work provides a more efficient alternative to time-consuming subjective evaluations for voice conversion researchers and practitioners, though it is incremental as it builds on existing challenge frameworks.
The study tackled the problem of evaluating voice conversion systems by comparing objective assessments with subjective listening tests from the Voice Conversion Challenge 2020, finding high correlations for measures like automatic speaker verification and automatic speech recognition, and identified some methods as high security risks.
The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary evaluation of the challenge submissions was done through crowd-sourced listening tests, we also performed an objective assessment of the submitted systems. The aim of the objective assessment is to provide complementary performance analysis that may be more beneficial than the time-consuming listening tests. In this study, we examined five types of objective assessments using automatic speaker verification (ASV), neural speaker embeddings, spoofing countermeasures, predicted mean opinion scores (MOS), and automatic speech recognition (ASR). Each of these objective measures assesses the VC output along different aspects. We observed that the correlations of these objective assessments with the subjective results were high for ASV, neural speaker embedding, and ASR, which makes them more influential for predicting subjective test results. In addition, we performed spoofing assessments on the submitted systems and identified some of the VC methods showing a potentially high security risk.