# Conditional Deep Hierarchical Variational Autoencoder for Voice Conversion

arXiv: https://arxiv.org/abs/2112.02796 · HTML: https://mlsanity.com/paper/2112.02796/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images](https://mlsanity.com/paper/2011.10650/) (2020)
- [AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss](https://mlsanity.com/paper/1905.05879/) (2019)
- [BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling](https://mlsanity.com/paper/1902.02102/) (2019)
- [Hierarchical Generative Modeling for Controllable Speech Synthesis](https://mlsanity.com/paper/1810.07217/) (2018)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks](https://mlsanity.com/paper/1806.02169/) (2018)
- [Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion](https://mlsanity.com/paper/2008.12527/) (2020)
- [Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder](https://mlsanity.com/paper/1610.04019/) (2016)
- [Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks](https://mlsanity.com/paper/1704.00849/) (2017)
- [VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture](https://mlsanity.com/paper/2006.04154/) (2020)
- [Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations](https://mlsanity.com/paper/1804.02812/) (2018)
- [AttS2S-VC: Sequence-to-Sequence Voice Conversion with Attention and Context Preservation Mechanisms](https://mlsanity.com/paper/1811.04076/) (2018)
- [Non-Parallel Voice Conversion with Cyclic Variational Autoencoder](https://mlsanity.com/paper/1907.10185/) (2019)
- [VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention](https://mlsanity.com/paper/2102.06431/) (2021)
- [ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder](https://mlsanity.com/paper/1808.05092/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond](https://mlsanity.com/paper/2204.09269/) (2022)
- [Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer](https://mlsanity.com/paper/2409.06096/) (2024)

## Abstract (arXiv)

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or discretizing latent variables, this paper investigates how an increasing model expressiveness has benefits and impacts on the VAE-VC. Specifically, we first analyze VAE-VC from a rate-distortion perspective, and point out that model expressiveness is significant for VAE-VC because rate and distortion reflect similarity and naturalness of converted speeches. Based on the analysis, we propose a novel VC method using a deep hierarchical VAE, which has high model expressiveness as well as having fast conversion speed thanks to its non-autoregressive decoder. Also, our analysis reveals another problem that similarity can be degraded when the latent variable of VAEs has redundant information. We address the problem by controlling the information contained in the latent variable using β-VAE objective. In the experiment using VCTK corpus, the proposed method achieved mean opinion scores higher than 3.5 on both naturalness and similarity in inter-gender settings, which are higher than the scores of existing autoencoder-based VC methods.