Voice Conversion From Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks

Abstract

Building a voice conversion (VC) system from non-parallel speech corpora is challenging but highly valuable in real application scenarios. In most situations, the source and the target speakers do not repeat the same texts or they may even speak different languages. In this case, one possible, although indirect, solution is to build a generative model for speech. Generative models focus on explaining the observations with latent variables instead of learning a pairwise transformation function, thereby bypassing the requirement of speech frame alignment. In this paper, we propose a non-parallel VC framework with a variational autoencoding Wasserstein generative adversarial network (VAW-GAN) that explicitly considers a VC objective when building the speech model. Experimental results corroborate the capability of our framework for building a VC system from unaligned data, and demonstrate improved conversion quality.

Stats

• citations150
• S2 citations—
• github stars0
• HF likes0
• heat score16.34
• arxiv keyhsu2017voice

Related papers

• CVC: Contrastive Learning For Non-parallel Voice Conversion (2020)7.50
• Starganv2-vc: A Diverse, Unsupervised, Non-parallel Framework For Natural-sounding Voice Conversion (2021)13.70
• Stargan-vc: Non-parallel Many-to-many Voice Conversion With Star Generative Adversarial Networks (2018)18.09
• An Adaptive Learning Based Generative Adversarial Network For One-to-one Voice Conversion (2021)10.61
• ACVAE-VC: Non-parallel Many-to-many Voice Conversion With Auxiliary Classifier Variational Autoencoder (2018)14.69
• Voice Conversion Based On Cross-domain Features Using Variational Auto Encoders (2018)11.29
• Subband-based Generative Adversarial Network For Non-parallel Many-to-many Voice Conversion (2022)0.00
• Nonparallel Voice Conversion With Augmented Classifier Star Generative Adversarial Networks (2020)9.92