EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Objective evaluation results comparison among VQ-VAE, CTC-VQ-VAE, FragmentVC, and the proposed method in terms of MCD

From: W2VC: WavLM representation based one-shot voice conversion with gradient reversal distillation and CTC supervision

Method	MCD(dB)
VQ-VAE	9.716
CTC-VQ-VAE	8.988
FragmentVC	10.204
W2VC	8.901

Back to article page