# CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer

arXiv: https://arxiv.org/abs/2111.15159 · HTML: https://mlsanity.com/paper/2111.15159/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 30 Nov 2021.

## Builds on (most cited first, 7 of 7)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data](https://mlsanity.com/paper/2002.00198/) (2020)
- [DA-Transformer: Distance-aware Transformer](https://mlsanity.com/paper/2010.06925/) (2020)
- [Nonparallel Emotional Speech Conversion](https://mlsanity.com/paper/1811.01174/) (2018)
- [ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion](https://mlsanity.com/paper/1811.01609/) (2018)
- [Emotional Voice Conversion With Cycle-consistent Adversarial Network](https://mlsanity.com/paper/2004.03781/) (2020)
- [StarGAN-based Emotional Voice Conversion for Japanese Phrases](https://mlsanity.com/paper/2104.01807/) (2021)

## Built on by (most cited first, 4 of 4)

- [Dance Style Transfer with Cross-modal Transformer](https://mlsanity.com/paper/2208.09406/) (2022)
- [EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion](https://mlsanity.com/paper/2412.20359/) (2024)
- [Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition](https://mlsanity.com/paper/2503.14513/) (2025)
- [Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation](https://mlsanity.com/paper/2508.09188/) (2025)

## Abstract (arXiv)

In this study, we explore the transformer's ability to capture intra-relations among frames by augmenting the receptive field of models. Concretely, we propose a CycleGAN-based model with the transformer and investigate its ability in the emotional voice conversion task. In the training procedure, we adopt curriculum learning to gradually increase the frame length so that the model can see from the short segment till the entire speech. The proposed method was evaluated on the Japanese emotional speech dataset and compared to several baselines (ACVAE, CycleGAN) with objective and subjective evaluations. The results show that our proposed model is able to convert emotion with higher strength and quality.