Many-to-many Voice Conversion Using Cycle-consistent Variational Autoencoder With Multiple Decoders

Abstract

One of the obstacles in many-to-many voice conversion is the requirement of the parallel training data, which contain pairs of utterances with the same linguistic content spoken by different speakers. Since collecting such parallel data is a highly expensive task, many works attempted to use non-parallel training data for many-to-many voice conversion. One of such approaches is using the variational autoencoder (VAE). Though it can handle many-to-many voice conversion without the parallel training, the VAE based voice conversion methods suffer from low sound qualities of the converted speech. One of the major reasons is because the VAE learns only the self-reconstruction path. The conversion path is not trained at all. In this paper, we propose a cycle consistency loss for VAE to explicitly learn the conversion path. In addition, we propose to use multiple decoders to further improve the sound qualities of the conventional VAE based voice conversion methods. The effectiveness of the pr

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keylee2019many

Related papers

• Enhanced Exemplar Autoencoder With Cycle Consistency Loss In Any-to-one Voice Conversion (2022)0.00
• Many-to-many Voice Conversion Using Conditional Cycle-consistent Adversarial Networks (2020)10.85
• Non-parallel Voice Conversion With Cyclic Variational Autoencoder (2019)12.10
• ACVAE-VC: Non-parallel Many-to-many Voice Conversion With Auxiliary Classifier Variational Autoencoder (2018)14.69
• CVC: Contrastive Learning For Non-parallel Voice Conversion (2020)7.50
• Conditional Deep Hierarchical Variational Autoencoder For Voice Conversion (2021)0.00
• Many-to-many Voice Conversion Based Feature Disentanglement Using Variational Autoencoder (2021)7.81
• F0-consistent Many-to-many Non-parallel Voice Conversion Via Conditional Autoencoder (2020)13.17