Adversarially learning disentangled speech representations for robust multi-factor voice conversion
This addresses the need for more controllable style transfer in voice conversion by enhancing robustness for multiple prosody-related factors, representing an incremental improvement over existing methods.
The paper tackled the problem of achieving robust multi-factor voice conversion by proposing an adversarial learning framework to disentangle speech representations for content, timbre, rhythm, and pitch, resulting in improved speech quality MOS from 2.79 to 3.30 and reduced MCD from 3.89 to 3.58.
Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and content, lacking controllability on other prosody-related factors. State-of-the-art speech representation learning methods for more speechfactors are using primary disentangle algorithms such as random resampling and ad-hoc bottleneck layer size adjustment,which however is hard to ensure robust speech representationdisentanglement. To increase the robustness of highly controllable style transfer on multiple factors in VC, we propose a disentangled speech representation learning framework based on adversarial learning. Four speech representations characterizing content, timbre, rhythm and pitch are extracted, and further disentangled by an adversarial Mask-And-Predict (MAP)network inspired by BERT. The adversarial network is used tominimize the correlations between the speech representations,by randomly masking and predicting one of the representationsfrom the others. Experimental results show that the proposedframework significantly improves the robustness of VC on multiple factors by increasing the speech quality MOS from 2.79 to3.30 and decreasing the MCD from 3.89 to 3.58.