# Non-Parallel Voice Conversion with Cyclic Variational Autoencoder

arXiv: https://arxiv.org/abs/1907.10185 · HTML: https://mlsanity.com/paper/1907.10185/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2019.

## Built on by (most cited first, 15 of 15)

- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder](https://mlsanity.com/paper/2107.06642/) (2021)
- [An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation](https://mlsanity.com/paper/2107.08361/) (2021)
- [FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation](https://mlsanity.com/paper/2409.02245/) (2024)
- [A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion](https://mlsanity.com/paper/2106.01415/) (2021)
- [Catch You and I Can: Revealing Source Voiceprint Against Voice Conversion](https://mlsanity.com/paper/2302.12434/) (2023)
- [ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization](https://mlsanity.com/paper/2506.01032/) (2025)
- [Axial Residual Networks for CycleGAN-based Voice Conversion](https://mlsanity.com/paper/2102.08075/) (2021)
- [Conditional Deep Hierarchical Variational Autoencoder for Voice Conversion](https://mlsanity.com/paper/2112.02796/) (2021)
- [Non-Parallel Voice Conversion for ASR Augmentation](https://mlsanity.com/paper/2209.06987/) (2022)
- [ALO-VC: Any-to-any Low-latency One-shot Voice Conversion](https://mlsanity.com/paper/2306.01100/) (2023)
- [LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models](https://mlsanity.com/paper/2509.08379/) (2025)
- [Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction](https://mlsanity.com/paper/2105.09858/) (2021)
- [CycleFlow: Purify Information Factors by Cycle Loss](https://mlsanity.com/paper/2110.09928/) (2021)
- [Voice Conversion with Denoising Diffusion Probabilistic GAN Models](https://mlsanity.com/paper/2308.14319/) (2023)

## Abstract (arXiv)

In this paper, we present a novel technique for a non-parallel voice conversion (VC) with the use of cyclic variational autoencoder (CycleVAE)-based spectral modeling. In a variational autoencoder(VAE) framework, a latent space, usually with a Gaussian prior, is used to encode a set of input features. In a VAE-based VC, the encoded latent features are fed into a decoder, along with speaker-coding features, to generate estimated spectra with either the original speaker identity (reconstructed) or another speaker identity (converted). Due to the non-parallel modeling condition, the converted spectra can not be directly optimized, which heavily degrades the performance of a VAE-based VC. In this work, to overcome this problem, we propose to use CycleVAE-based spectral model that indirectly optimizes the conversion flow by recycling the converted features back into the system to obtain corresponding cyclic reconstructed spectra that can be directly optimized. The cyclic flow can be continued by using the cyclic reconstructed features as input for the next cycle. The experimental results demonstrate the effectiveness of the proposed CycleVAE-based VC, which yields higher accuracy of converted spectra, generates latent features with higher correlation degree, and significantly improves the quality and conversion accuracy of the converted speech.