Related papers: StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

URL: http://arxiv.org/abs/2107.10394v2
Date: Fri, 23 Jul 2021 01:08:09 GMT
Title: StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
Authors: Yinghao Aaron Li, Ali Zare, Nima Mesgarani
Abstract summary: We present an unsupervised many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Our model is trained only with 20 English speakers. It generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion.
Score: 19.74933410443264
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: We present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model significantly outperforms previous VC models. Although our model is trained only with 20 English speakers, it generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion. Using a style encoder, our framework can also convert plain reading speech into stylistic speech, such as emotional and falsetto speech. Subjective and objective evaluation experiments on a non-parallel many-to-many voice conversion task revealed that our model produces natural sounding voices, close to the sound quality of state-of-the-art text-to-speech (TTS) based voice conversion methods without the need for text labels. Moreover, our model is completely convolutional and with a faster-than-real-time vocoder such as Parallel WaveGAN can perform real-time voice conversion.