Fig. 9From: W2VC: WavLM representation based one-shot voice conversion with gradient reversal distillation and CTC supervisiona Mel-spectrogram of ground truth (arctic_a0002 of the source speaker “rms” in the CMU corpus). b W2VC cross-gender conversion, Mel-spectrogram of the target speaker “slt”. c W2VC same-gender conversion, Mel-spectrogram of the target speaker “bdl”Back to article page