# Many-to-Many Voice Conversion using Conditional Cycle-Consistent Adversarial Networks

arXiv: https://arxiv.org/abs/2002.06328 · HTML: https://mlsanity.com/paper/2002.06328/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2205.06445/) (2022)
- [Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder](https://mlsanity.com/paper/2107.06642/) (2021)
- [Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning](https://mlsanity.com/paper/2505.15402/) (2025)
- [Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks](https://mlsanity.com/paper/2110.01164/) (2021)
- [An Adaptive Learning based Generative Adversarial Network for One-To-One Voice Conversion](https://mlsanity.com/paper/2104.12159/) (2021)
- [Music Sentiment Transfer](https://mlsanity.com/paper/2110.05765/) (2021)
- [CycleFlow: Purify Information Factors by Cycle Loss](https://mlsanity.com/paper/2110.09928/) (2021)
- [Artificial ASMR: A Cyber-Psychological Approach](https://mlsanity.com/paper/2210.14321/) (2022)

## Abstract (arXiv)

Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire. Recently, the cycle-consistent adversarial network (CycleGAN), which does not require parallel training data, has been applied to voice conversion, showing the state-of-the-art performance. The CycleGAN based voice conversion, however, can be used only for a pair of speakers, i.e., one-to-one voice conversion between two speakers. In this paper, we extend the CycleGAN by conditioning the network on speakers. As a result, the proposed method can perform many-to-many voice conversion among multiple speakers using a single generative adversarial network (GAN). Compared to building multiple CycleGANs for each pair of speakers, the proposed method reduces the computational and spatial cost significantly without compromising the sound quality of the converted voice. Experimental results using the VCC2018 corpus confirm the efficiency of the proposed method.