Speech representation disentanglement with adversarial mutual information learning for one-shot voice conversion
One-shot voice conversion (VC) with only a single target speaker's speech for reference has
become a hot research topic. Existing works generally disentangle timbre, while information …
become a hot research topic. Existing works generally disentangle timbre, while information …
Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
SC Yang, M Tantrawenith, H Zhuang, Z Wu… - arXiv e …, 2022 - ui.adsabs.harvard.edu
One-shot voice conversion (VC) with only a single target speaker's speech for reference has
become a hot research topic. Existing works generally disentangle timbre, while information …
become a hot research topic. Existing works generally disentangle timbre, while information …
[PDF][PDF] Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
S Yang, M Tantrawenith, H Zhuang, Z Wu, A Sun… - 2022 - scholar.archive.org
One-shot voice conversion (VC) with only a single targetspeaker's speech for reference has
become a hot research topic. Existing works generally disentangle timbre, while information …
become a hot research topic. Existing works generally disentangle timbre, while information …
[PDF][PDF] Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
S Yang, M Tantrawenith, H Zhuang, Z Wu, A Sun… - 2022 - isca-archive.org
One-shot voice conversion (VC) with only a single targetspeaker's speech for reference has
become a hot research topic. Existing works generally disentangle timbre, while information …
become a hot research topic. Existing works generally disentangle timbre, while information …